Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3809 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4371. Min Range: -7.4371
Max Act: 7.4371. Min Act: -0.1700
Data Index: 320266 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4371. Min Range: -7.4371
Max Act: 7.2184. Min Act: -0.1700
Data Index: 6011968 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4371. Min Range: -7.4371
Max Act: 7.1246. Min Act: -0.1700
Data Index: 7920960 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4371. Min Range: -7.4371
Max Act: 7.0309. Min Act: -0.1700
Data Index: 2413608 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.9371. Min Act: -0.1700
Data Index: 1609729 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.9059. Min Act: -0.1700
Data Index: 2127677 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.9059. Min Act: -0.1700
Data Index: 7697624 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.8746. Min Act: -0.1700
Data Index: 2099173 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.8121. Min Act: -0.1700
Data Index: 6050028 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.8121. Min Act: -0.1700
Data Index: 4315160 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.8121. Min Act: -0.1700
Data Index: 4067347 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.7496. Min Act: -0.1700
Data Index: 5056731 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.7809. Min Act: -0.1700
Data Index: 2095047 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.7496. Min Act: -0.1700
Data Index: 945697 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.7184. Min Act: -0.1700
Data Index: 5387172 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.7184. Min Act: -0.1700
Data Index: 2346833 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.7184. Min Act: -0.1700
Data Index: 4752649 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.7184. Min Act: -0.1700
Data Index: 6943630 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.7184. Min Act: -0.1700
Data Index: 7554265 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4371. Min Range: -7.4371
Max Act: 6.6871. Min Act: -0.1700
Data Index: 4432369 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19