Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1605 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.4391. Min Act: -0.1700
Data Index: 3007618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.4391. Min Act: -0.1700
Data Index: 1104840 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.4391. Min Act: -0.1700
Data Index: 3229715 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3766. Min Act: -0.1700
Data Index: 5402604 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3766. Min Act: -0.1700
Data Index: 1485325 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3766. Min Act: -0.1700
Data Index: 7322587 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3766. Min Act: -0.1700
Data Index: 3716915 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3766. Min Act: -0.1700
Data Index: 6627641 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3141. Min Act: -0.1700
Data Index: 4508542 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3141. Min Act: -0.1700
Data Index: 4556075 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.2828. Min Act: -0.1700
Data Index: 5318101 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3141. Min Act: -0.1700
Data Index: 4452129 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3141. Min Act: -0.1700
Data Index: 4719327 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3141. Min Act: -0.1700
Data Index: 5515501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3141. Min Act: -0.1698
Data Index: 2738167 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.2828. Min Act: -0.1700
Data Index: 5839351 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.3141. Min Act: -0.1700
Data Index: 1475802 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.2828. Min Act: -0.1700
Data Index: 3838828 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.2828. Min Act: -0.1700
Data Index: 5733348 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4391. Min Range: -6.4391
Max Act: 6.2828. Min Act: -0.1700
Data Index: 1034928 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19