Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0953. Min Range: -7.0953
Max Act: 7.0953. Min Act: -0.1700
Data Index: 210076 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0953. Min Range: -7.0953
Max Act: 7.0328. Min Act: -0.1700
Data Index: 6718282 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.8140. Min Act: -0.1700
Data Index: 7538145 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7203. Min Act: -0.1700
Data Index: 4295633 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6265. Min Act: -0.1700
Data Index: 3877179 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.5640. Min Act: -0.1700
Data Index: 5186720 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.5015. Min Act: -0.1700
Data Index: 752712 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.4703. Min Act: -0.1700
Data Index: 4801812 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.4390. Min Act: -0.1700
Data Index: 1034104 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.4390. Min Act: -0.1700
Data Index: 3539866 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.4078. Min Act: -0.1700
Data Index: 7091820 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.4390. Min Act: -0.1700
Data Index: 197328 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.3765. Min Act: -0.1700
Data Index: 6195929 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.2828. Min Act: -0.1700
Data Index: 8552244 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.3140. Min Act: -0.1700
Data Index: 5925610 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.3140. Min Act: -0.1700
Data Index: 5776165 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.2828. Min Act: -0.1700
Data Index: 6312711 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.2828. Min Act: -0.1700
Data Index: 1493729 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.3140. Min Act: -0.1700
Data Index: 6532315 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.2515. Min Act: -0.1700
Data Index: 4329031 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19