Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2764 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.5644. Min Act: -0.1700
Data Index: 1935118 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.5331. Min Act: -0.1700
Data Index: 35277 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.3144. Min Act: -0.1700
Data Index: 7617575 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.0644. Min Act: -0.1700
Data Index: 3642548 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.0331. Min Act: -0.1700
Data Index: 223834 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.0019. Min Act: -0.1700
Data Index: 3945701 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.0331. Min Act: -0.1700
Data Index: 8139033 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.0019. Min Act: -0.1700
Data Index: 6051432 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.0019. Min Act: -0.1700
Data Index: 5660586 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5644. Min Range: -7.5644
Max Act: 7.0019. Min Act: -0.1700
Data Index: 6354858 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.9394. Min Act: -0.1700
Data Index: 8324551 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.9081. Min Act: -0.1700
Data Index: 5280146 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.8769. Min Act: -0.1700
Data Index: 3463846 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.8769. Min Act: -0.1700
Data Index: 5980527 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.9394. Min Act: -0.1700
Data Index: 529649 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.8769. Min Act: -0.1700
Data Index: 3068217 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.8456. Min Act: -0.1700
Data Index: 7721340 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.8456. Min Act: -0.1700
Data Index: 549538 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.8144. Min Act: -0.1700
Data Index: 1148058 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5644. Min Range: -7.5644
Max Act: 6.8456. Min Act: -0.1700
Data Index: 8105881 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19