Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 601 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1737. Min Range: -6.1737
Max Act: 6.1737. Min Act: -0.1700
Data Index: 5735870 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1737. Min Range: -6.1737
Max Act: 6.1424. Min Act: -0.1700
Data Index: 85659 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1737. Min Range: -6.1737
Max Act: 6.0487. Min Act: -0.1700
Data Index: 6232979 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1737. Min Range: -6.1737
Max Act: 6.0487. Min Act: -0.1700
Data Index: 3752185 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1737. Min Range: -6.1737
Max Act: 6.0174. Min Act: -0.1700
Data Index: 86839 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.9862. Min Act: -0.1700
Data Index: 7041546 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.9862. Min Act: -0.1700
Data Index: 4467612 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.9549. Min Act: -0.1700
Data Index: 2351541 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.9862. Min Act: -0.1700
Data Index: 6896259 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.8924. Min Act: -0.1700
Data Index: 6813816 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.8612. Min Act: -0.1700
Data Index: 86838 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.9237. Min Act: -0.1700
Data Index: 4488407 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.8612. Min Act: -0.1700
Data Index: 7922236 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.8924. Min Act: -0.1700
Data Index: 3757678 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.8612. Min Act: -0.1700
Data Index: 4893010 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.8612. Min Act: -0.1700
Data Index: 1459028 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.8299. Min Act: -0.1700
Data Index: 2859411 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.8299. Min Act: -0.1700
Data Index: 1884993 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.8299. Min Act: -0.1700
Data Index: 7548518 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1737. Min Range: -6.1737
Max Act: 5.7987. Min Act: -0.1700
Data Index: 7117215 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19