Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.5060. Min Act: -0.1700
Data Index: 3723389 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.4122. Min Act: -0.1700
Data Index: 5451587 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.3497. Min Act: -0.1700
Data Index: 3679025 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.3185. Min Act: -0.1700
Data Index: 3278412 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2872. Min Act: -0.1700
Data Index: 3833914 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2872. Min Act: -0.1700
Data Index: 5419254 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2872. Min Act: -0.1700
Data Index: 4155638 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2872. Min Act: -0.1700
Data Index: 6006720 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2247. Min Act: -0.1700
Data Index: 5816272 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2247. Min Act: -0.1700
Data Index: 8147250 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2247. Min Act: -0.1700
Data Index: 2390895 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2247. Min Act: -0.1700
Data Index: 6262347 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2247. Min Act: -0.1700
Data Index: 5832784 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.2247. Min Act: -0.1700
Data Index: 8173230 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.1935. Min Act: -0.1700
Data Index: 4563896 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.1935. Min Act: -0.1700
Data Index: 2291745 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.1622. Min Act: -0.1700
Data Index: 573500 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.1622. Min Act: -0.1700
Data Index: 592488 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.1622. Min Act: -0.1700
Data Index: 7220068 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5060. Min Range: -6.5060
Max Act: 6.1622. Min Act: -0.1700
Data Index: 3357176 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19