Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2068 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.0394. Min Range: -11.0394
Max Act: 11.0394. Min Act: -0.1700
Data Index: 2064653 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.6644. Min Act: -0.1700
Data Index: 7217076 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.4769. Min Act: -0.1700
Data Index: 8222347 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.5394. Min Act: -0.1700
Data Index: 1017250 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.4144. Min Act: -0.1700
Data Index: 3974273 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.2894. Min Act: -0.1700
Data Index: 8417856 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.2894. Min Act: -0.1700
Data Index: 5732270 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.3519. Min Act: -0.1700
Data Index: 1138287 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.2894. Min Act: -0.1700
Data Index: 4843175 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.2269. Min Act: -0.1700
Data Index: 7620206 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.1644. Min Act: -0.1700
Data Index: 1621572 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0394. Min Range: -11.0394
Max Act: 9.9769. Min Act: -0.1700
Data Index: 7115093 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.1019. Min Act: -0.1700
Data Index: 370198 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0394. Min Range: -11.0394
Max Act: 10.1019. Min Act: -0.1700
Data Index: 8180405 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0394. Min Range: -11.0394
Max Act: 9.9769. Min Act: -0.1700
Data Index: 4639543 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0394. Min Range: -11.0394
Max Act: 9.9769. Min Act: -0.1700
Data Index: 5505255 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0394. Min Range: -11.0394
Max Act: 9.9769. Min Act: -0.1700
Data Index: 7659585 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0394. Min Range: -11.0394
Max Act: 9.9144. Min Act: -0.1700
Data Index: 2665961 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0394. Min Range: -11.0394
Max Act: 9.9144. Min Act: -0.1700
Data Index: 5518626 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0394. Min Range: -11.0394
Max Act: 9.9769. Min Act: -0.1700
Data Index: 5782566 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19