Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4422 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3299. Min Range: -6.3299
Max Act: 6.3299. Min Act: -0.1700
Data Index: 3583147 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3299. Min Range: -6.3299
Max Act: 6.2674. Min Act: -0.1700
Data Index: 2884638 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3299. Min Range: -6.3299
Max Act: 6.1112. Min Act: -0.1700
Data Index: 8645001 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3299. Min Range: -6.3299
Max Act: 6.0799. Min Act: -0.1700
Data Index: 5393113 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.8924. Min Act: -0.1700
Data Index: 5116970 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.9549. Min Act: -0.1700
Data Index: 336993 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.8924. Min Act: -0.1700
Data Index: 79328 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.8299. Min Act: -0.1700
Data Index: 1159710 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.8299. Min Act: -0.1700
Data Index: 3061275 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.8299. Min Act: -0.1700
Data Index: 4093912 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7987. Min Act: -0.1700
Data Index: 2859717 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7987. Min Act: -0.1700
Data Index: 8144193 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7674. Min Act: -0.1700
Data Index: 4093913 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7674. Min Act: -0.1700
Data Index: 2213593 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7674. Min Act: -0.1700
Data Index: 2120627 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7362. Min Act: -0.1700
Data Index: 7991475 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7362. Min Act: -0.1700
Data Index: 5220374 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7362. Min Act: -0.1700
Data Index: 8697591 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7049. Min Act: -0.1700
Data Index: 712913 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3299. Min Range: -6.3299
Max Act: 5.7049. Min Act: -0.1700
Data Index: 8711280 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19