Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.6505. Min Act: -0.1700
Data Index: 487488 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.4630. Min Act: -0.1700
Data Index: 4998943 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.4317. Min Act: -0.1700
Data Index: 5868887 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.4317. Min Act: -0.1700
Data Index: 3591482 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.4317. Min Act: -0.1700
Data Index: 7759551 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.3380. Min Act: -0.1700
Data Index: 3313030 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.3067. Min Act: -0.1700
Data Index: 2249599 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.1817. Min Act: -0.1700
Data Index: 2926067 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.1505. Min Act: -0.1700
Data Index: 4111836 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.1192. Min Act: -0.1700
Data Index: 7970905 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.1192. Min Act: -0.1700
Data Index: 7284449 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.1192. Min Act: -0.1700
Data Index: 7741774 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.1192. Min Act: -0.1700
Data Index: 5070342 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.0880. Min Act: -0.1700
Data Index: 8016734 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.0880. Min Act: -0.1700
Data Index: 3386171 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.1192. Min Act: -0.1700
Data Index: 2568468 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.0255. Min Act: -0.1700
Data Index: 2245001 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.0255. Min Act: -0.1700
Data Index: 3342604 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6505. Min Range: -7.6505
Max Act: 7.0255. Min Act: -0.1700
Data Index: 2530295 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6505. Min Range: -7.6505
Max Act: 6.9942. Min Act: -0.1700
Data Index: 8682 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19