Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2540 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0780. Min Range: -5.0780
Max Act: 5.0780. Min Act: -0.1700
Data Index: 2896649 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0780. Min Range: -5.0780
Max Act: 5.0780. Min Act: -0.1700
Data Index: 8710870 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.9843. Min Act: -0.1700
Data Index: 8157328 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.9843. Min Act: -0.1700
Data Index: 7973903 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.8280. Min Act: -0.1700
Data Index: 192182 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.8280. Min Act: -0.1700
Data Index: 5783071 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.7655. Min Act: -0.1700
Data Index: 8347099 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.7343. Min Act: -0.1700
Data Index: 725014 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.7343. Min Act: -0.1700
Data Index: 8242337 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.7030. Min Act: -0.1700
Data Index: 8288378 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.7030. Min Act: -0.1700
Data Index: 2152369 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.7030. Min Act: -0.1700
Data Index: 8054488 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.7030. Min Act: -0.1700
Data Index: 3444304 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.6718. Min Act: -0.1700
Data Index: 7958844 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.6718. Min Act: -0.1700
Data Index: 4288683 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.6718. Min Act: -0.1700
Data Index: 3287910 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.6718. Min Act: -0.1700
Data Index: 527248 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.6718. Min Act: -0.1700
Data Index: 5066404 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.6718. Min Act: -0.1700
Data Index: 4401583 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0780. Min Range: -5.0780
Max Act: 4.6405. Min Act: -0.1700
Data Index: 420051 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19