Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.2594. Min Act: -0.1700
Data Index: 4417769 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.2594. Min Act: -0.1700
Data Index: 3664233 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.1969. Min Act: -0.1700
Data Index: 3854028 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.1031. Min Act: -0.1700
Data Index: 2001460 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0406. Min Act: -0.1700
Data Index: 8411712 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0406. Min Act: -0.1700
Data Index: 3233123 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0406. Min Act: -0.1700
Data Index: 3800432 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0406. Min Act: -0.1700
Data Index: 1139365 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0406. Min Act: -0.1700
Data Index: 2249868 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 4135200 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 4230152 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 786475 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 7695809 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2594. Min Range: -7.2594
Max Act: 7.0094. Min Act: -0.1700
Data Index: 6576680 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2594. Min Range: -7.2594
Max Act: 6.9469. Min Act: -0.1700
Data Index: 2561601 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2594. Min Range: -7.2594
Max Act: 6.9469. Min Act: -0.1700
Data Index: 4137096 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2594. Min Range: -7.2594
Max Act: 6.9469. Min Act: -0.1700
Data Index: 4196766 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2594. Min Range: -7.2594
Max Act: 6.9469. Min Act: -0.1700
Data Index: 7570214 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2594. Min Range: -7.2594
Max Act: 6.9156. Min Act: -0.1700
Data Index: 838304 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2594. Min Range: -7.2594
Max Act: 6.9156. Min Act: -0.1700
Data Index: 6424526 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19