Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1501 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.5122. Min Act: -0.1700
Data Index: 6670881 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.3872. Min Act: -0.1700
Data Index: 616121 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.3559. Min Act: -0.1700
Data Index: 4182595 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.2622. Min Act: -0.1700
Data Index: 6528284 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.2309. Min Act: -0.1700
Data Index: 5176156 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.2309. Min Act: -0.1700
Data Index: 5682361 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.1997. Min Act: -0.1700
Data Index: 748494 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.2309. Min Act: -0.1700
Data Index: 3392169 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.1684. Min Act: -0.1700
Data Index: 8466014 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.1372. Min Act: -0.1700
Data Index: 6226951 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.1059. Min Act: -0.1700
Data Index: 598040 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.1684. Min Act: -0.1700
Data Index: 1771833 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.1372. Min Act: -0.1700
Data Index: 8790469 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.1059. Min Act: -0.1700
Data Index: 2932620 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.1059. Min Act: -0.1700
Data Index: 7759091 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.0747. Min Act: -0.1700
Data Index: 6496447 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.0747. Min Act: -0.1700
Data Index: 7432809 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.0434. Min Act: -0.1700
Data Index: 599332 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.1059. Min Act: -0.1700
Data Index: 2731582 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5122. Min Range: -5.5122
Max Act: 5.0434. Min Act: -0.1700
Data Index: 4777737 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19