Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0459. Min Range: -3.0459
Max Act: 3.0459. Min Act: -0.1700
Data Index: 6805320 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.8877. Min Act: -0.1700
Data Index: 2334416 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.7444. Min Act: -0.1700
Data Index: 6432305 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.6965. Min Act: -0.1700
Data Index: 520143 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.6805. Min Act: -0.1700
Data Index: 7197840 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.6644. Min Act: -0.1700
Data Index: 2353610 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.6163. Min Act: -0.1700
Data Index: 6175370 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.6163. Min Act: -0.1700
Data Index: 6859465 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.6002. Min Act: -0.1700
Data Index: 3924280 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.6002. Min Act: -0.1700
Data Index: 6850297 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.5841. Min Act: -0.1700
Data Index: 4517208 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.5680. Min Act: -0.1700
Data Index: 5084136 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.5357. Min Act: -0.1700
Data Index: 4148271 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.5357. Min Act: -0.1700
Data Index: 8389854 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.5518. Min Act: -0.1700
Data Index: 6154151 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.5195. Min Act: -0.1700
Data Index: 1336335 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.5357. Min Act: -0.1700
Data Index: 4275864 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.5195. Min Act: -0.1700
Data Index: 7722466 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.4871. Min Act: -0.1700
Data Index: 6020986 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0459. Min Range: -3.0459
Max Act: 2.4871. Min Act: -0.1700
Data Index: 897964 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19