Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.4523. Min Act: -0.1700
Data Index: 4526093 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.4523. Min Act: -0.1700
Data Index: 3260626 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.2023. Min Act: -0.1700
Data Index: 1370965 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.1086. Min Act: -0.1700
Data Index: 2603784 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.1086. Min Act: -0.1700
Data Index: 5231289 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.1086. Min Act: -0.1700
Data Index: 1977190 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.1086. Min Act: -0.1700
Data Index: 5363484 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0773. Min Act: -0.1700
Data Index: 1839140 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0461. Min Act: -0.1700
Data Index: 506600 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0461. Min Act: -0.1700
Data Index: 1589062 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0461. Min Act: -0.1700
Data Index: 7845894 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0461. Min Act: -0.1700
Data Index: 2313919 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0461. Min Act: -0.1700
Data Index: 2714600 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0148. Min Act: -0.1700
Data Index: 6003009 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0148. Min Act: -0.1700
Data Index: 3751705 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0148. Min Act: -0.1700
Data Index: 8383663 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0148. Min Act: -0.1700
Data Index: 910902 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0461. Min Act: -0.1700
Data Index: 5213291 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4523. Min Range: -5.4523
Max Act: 5.0148. Min Act: -0.1700
Data Index: 7318336 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4523. Min Range: -5.4523
Max Act: 4.9836. Min Act: -0.1700
Data Index: 5493676 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19