Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 540 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.8966. Min Act: -0.1700
Data Index: 7416491 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.8341. Min Act: -0.1700
Data Index: 745482 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.4278. Min Act: -0.1700
Data Index: 4890648 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.4278. Min Act: -0.1700
Data Index: 8456510 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.3966. Min Act: -0.1700
Data Index: 5535088 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.3653. Min Act: -0.1700
Data Index: 6273844 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.3028. Min Act: -0.1700
Data Index: 8393698 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.2091. Min Act: -0.1700
Data Index: 3481955 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.2403. Min Act: -0.1700
Data Index: 3953963 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1778. Min Act: -0.1700
Data Index: 3483344 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1778. Min Act: -0.1700
Data Index: 1024693 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1778. Min Act: -0.1700
Data Index: 3465574 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1466. Min Act: -0.1700
Data Index: 7942197 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1466. Min Act: -0.1700
Data Index: 7257258 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1466. Min Act: -0.1700
Data Index: 8106195 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1466. Min Act: -0.1700
Data Index: 8268920 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1466. Min Act: -0.1700
Data Index: 8286963 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1466. Min Act: -0.1700
Data Index: 6643971 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1153. Min Act: -0.1700
Data Index: 7634627 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8966. Min Range: -5.8966
Max Act: 5.1153. Min Act: -0.1700
Data Index: 5727557 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19