Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.6470. Min Act: -0.1700
Data Index: 3317235 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.6158. Min Act: -0.1700
Data Index: 7938520 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.5845. Min Act: -0.1700
Data Index: 8127171 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.5220. Min Act: -0.1700
Data Index: 6173614 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.5533. Min Act: -0.1700
Data Index: 7294241 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.4595. Min Act: -0.1700
Data Index: 8534931 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.4283. Min Act: -0.1700
Data Index: 2034617 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.4283. Min Act: -0.1700
Data Index: 7852912 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.4595. Min Act: -0.1700
Data Index: 5818354 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.4595. Min Act: -0.1700
Data Index: 5173563 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.4283. Min Act: -0.1700
Data Index: 7342114 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.4283. Min Act: -0.1700
Data Index: 6454308 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3970. Min Act: -0.1700
Data Index: 3394428 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3970. Min Act: -0.1700
Data Index: 7744673 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3970. Min Act: -0.1700
Data Index: 2021007 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3970. Min Act: -0.1700
Data Index: 2524090 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3658. Min Act: -0.1700
Data Index: 1362881 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3658. Min Act: -0.1700
Data Index: 7600377 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3345. Min Act: -0.1700
Data Index: 1970751 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6470. Min Range: -6.6470
Max Act: 6.3345. Min Act: -0.1700
Data Index: 683351 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19