Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1145 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2251. Min Range: -3.2251
Max Act: 3.2251. Min Act: -0.1700
Data Index: 2298839 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2251. Min Range: -3.2251
Max Act: 3.1465. Min Act: -0.1700
Data Index: 676111 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2251. Min Range: -3.2251
Max Act: 3.1307. Min Act: -0.1700
Data Index: 3787678 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2251. Min Range: -3.2251
Max Act: 3.0992. Min Act: -0.1700
Data Index: 6722802 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9887. Min Act: -0.1700
Data Index: 879535 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2251. Min Range: -3.2251
Max Act: 3.0045. Min Act: -0.1700
Data Index: 8411695 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2251. Min Range: -3.2251
Max Act: 3.0045. Min Act: -0.1700
Data Index: 1775659 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9887. Min Act: -0.1700
Data Index: 4311818 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9887. Min Act: -0.1700
Data Index: 1846276 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9571. Min Act: -0.1700
Data Index: 7941086 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9571. Min Act: -0.1700
Data Index: 8730936 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9571. Min Act: -0.1700
Data Index: 3572172 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9571. Min Act: -0.1700
Data Index: 2349388 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9571. Min Act: -0.1700
Data Index: 522238 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9413. Min Act: -0.1700
Data Index: 4420476 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9571. Min Act: -0.1700
Data Index: 2846755 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9413. Min Act: -0.1700
Data Index: 1755048 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9571. Min Act: -0.1700
Data Index: 1113199 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9571. Min Act: -0.1700
Data Index: 3164175 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2251. Min Range: -3.2251
Max Act: 2.9413. Min Act: -0.1700
Data Index: 5255946 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19