Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.6378. Min Act: -0.1700
Data Index: 5115225 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.6056. Min Act: -0.1700
Data Index: 7378131 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.6056. Min Act: -0.1700
Data Index: 5981228 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.5573. Min Act: -0.1700
Data Index: 505884 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.5573. Min Act: -0.1700
Data Index: 2173147 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.5573. Min Act: -0.1700
Data Index: 3934975 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.5250. Min Act: -0.1700
Data Index: 3157503 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.4926. Min Act: -0.1700
Data Index: 4877042 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.4764. Min Act: -0.1700
Data Index: 2818873 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.4764. Min Act: -0.1700
Data Index: 7464088 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.4439. Min Act: -0.1700
Data Index: 7354040 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.4439. Min Act: -0.1700
Data Index: 4077746 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.4276. Min Act: -0.1700
Data Index: 2991862 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.4113. Min Act: -0.1700
Data Index: 3279043 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.4113. Min Act: -0.1700
Data Index: 4979512 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.3786. Min Act: -0.1700
Data Index: 2609809 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.4113. Min Act: -0.1700
Data Index: 2866876 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.3786. Min Act: -0.1700
Data Index: 2586035 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.3786. Min Act: -0.1700
Data Index: 3000377 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6378. Min Range: -2.6378
Max Act: 2.3786. Min Act: -0.1700
Data Index: 5762370 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19