Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0093. Min Range: -4.0093
Max Act: 4.0093. Min Act: -0.1700
Data Index: 93041 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.9780. Min Act: -0.1700
Data Index: 1874301 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.9155. Min Act: -0.1700
Data Index: 4511906 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.7748. Min Act: -0.1700
Data Index: 3511045 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.7904. Min Act: -0.1700
Data Index: 3165409 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.7748. Min Act: -0.1700
Data Index: 4969093 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.7591. Min Act: -0.1700
Data Index: 3077938 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.7435. Min Act: -0.1700
Data Index: 1681853 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.7435. Min Act: -0.1700
Data Index: 233662 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.7279. Min Act: -0.1700
Data Index: 364204 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.6966. Min Act: -0.1700
Data Index: 2873026 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.7122. Min Act: -0.1700
Data Index: 463358 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.6966. Min Act: -0.1700
Data Index: 1080066 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.6809. Min Act: -0.1700
Data Index: 7264982 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.6496. Min Act: -0.1700
Data Index: 6220082 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.6496. Min Act: -0.1700
Data Index: 4629323 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.6496. Min Act: -0.1700
Data Index: 7237687 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.6496. Min Act: -0.1700
Data Index: 3263545 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.6183. Min Act: -0.1700
Data Index: 5651025 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0093. Min Range: -4.0093
Max Act: 3.6340. Min Act: -0.1700
Data Index: 7178831 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19