Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2274 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.9445. Min Act: -0.1700
Data Index: 2108037 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.9132. Min Act: -0.1700
Data Index: 1812931 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.8820. Min Act: -0.1700
Data Index: 4308885 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.8820. Min Act: -0.1700
Data Index: 8563379 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.9132. Min Act: -0.1700
Data Index: 7722248 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.7570. Min Act: -0.1700
Data Index: 1730337 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.7257. Min Act: -0.1700
Data Index: 8100127 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.7257. Min Act: -0.1700
Data Index: 8761908 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.6945. Min Act: -0.1700
Data Index: 2422997 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.7257. Min Act: -0.1700
Data Index: 8486502 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.6320. Min Act: -0.1700
Data Index: 1590476 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.6632. Min Act: -0.1700
Data Index: 5087418 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.6007. Min Act: -0.1700
Data Index: 4155572 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.6007. Min Act: -0.1700
Data Index: 5179234 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.6007. Min Act: -0.1700
Data Index: 8182592 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.5695. Min Act: -0.1700
Data Index: 2324 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.5695. Min Act: -0.1700
Data Index: 3355529 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.5695. Min Act: -0.1700
Data Index: 1230393 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.5382. Min Act: -0.1700
Data Index: 7985515 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9445. Min Range: -6.9445
Max Act: 6.5382. Min Act: -0.1700
Data Index: 2046577 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19