Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.9749. Min Act: -0.1700
Data Index: 8539169 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.9436. Min Act: -0.1700
Data Index: 3160718 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.8186. Min Act: -0.1700
Data Index: 1429781 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.8186. Min Act: -0.1700
Data Index: 926092 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.8186. Min Act: -0.1700
Data Index: 383180 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7874. Min Act: -0.1700
Data Index: 1177645 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.8186. Min Act: -0.1699
Data Index: 2200477 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.8186. Min Act: -0.1700
Data Index: 5904460 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7874. Min Act: -0.1700
Data Index: 2794530 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7561. Min Act: -0.1700
Data Index: 8620734 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7249. Min Act: -0.1700
Data Index: 3713259 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7561. Min Act: -0.1700
Data Index: 7652391 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7561. Min Act: -0.1700
Data Index: 7642987 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7249. Min Act: -0.1700
Data Index: 6053631 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7561. Min Act: -0.1700
Data Index: 5562677 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7561. Min Act: -0.1700
Data Index: 5727374 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7561. Min Act: -0.1700
Data Index: 7080817 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7249. Min Act: -0.1700
Data Index: 840657 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7249. Min Act: -0.1700
Data Index: 2680268 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7249. Min Act: -0.1699
Data Index: 7058986 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19