Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4356. Min Range: -10.4356
Max Act: 10.4356. Min Act: -0.1700
Data Index: 1552667 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4356. Min Range: -10.4356
Max Act: 10.1856. Min Act: -0.1700
Data Index: 8437191 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4356. Min Range: -10.4356
Max Act: 10.1231. Min Act: -0.1700
Data Index: 7383473 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4356. Min Range: -10.4356
Max Act: 10.1231. Min Act: -0.1700
Data Index: 5368852 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4356. Min Range: -10.4356
Max Act: 10.0606. Min Act: -0.1700
Data Index: 5964299 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4356. Min Range: -10.4356
Max Act: 10.0606. Min Act: -0.1700
Data Index: 930757 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4356. Min Range: -10.4356
Max Act: 10.0606. Min Act: -0.1700
Data Index: 3085553 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4356. Min Range: -10.4356
Max Act: 10.0606. Min Act: -0.1700
Data Index: 1165430 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.9981. Min Act: -0.1700
Data Index: 5171203 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.9356. Min Act: -0.1700
Data Index: 6725734 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.8731. Min Act: -0.1700
Data Index: 3654653 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.8731. Min Act: -0.1700
Data Index: 3736039 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.8106. Min Act: -0.1700
Data Index: 305857 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.8106. Min Act: -0.1700
Data Index: 1298416 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.8106. Min Act: -0.1700
Data Index: 8640086 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.7481. Min Act: -0.1700
Data Index: 7371213 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.7481. Min Act: -0.1700
Data Index: 3233440 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.7481. Min Act: -0.1700
Data Index: 8332198 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.6856. Min Act: -0.1700
Data Index: 7206581 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4356. Min Range: -10.4356
Max Act: 9.6856. Min Act: -0.1700
Data Index: 3316104 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19