Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 519 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.8188. Min Act: -0.1700
Data Index: 957449 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.8188. Min Act: -0.1700
Data Index: 8116876 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.7563. Min Act: -0.1700
Data Index: 6401830 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.6938. Min Act: -0.1700
Data Index: 6035998 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.6626. Min Act: -0.1700
Data Index: 4834716 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.6626. Min Act: -0.1700
Data Index: 7866366 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.6626. Min Act: -0.1700
Data Index: 7866364 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.6313. Min Act: -0.1700
Data Index: 5196797 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.6001. Min Act: -0.1700
Data Index: 1410581 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.6001. Min Act: -0.1700
Data Index: 8134229 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.6001. Min Act: -0.1700
Data Index: 434245 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.5688. Min Act: -0.1700
Data Index: 5153701 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.5376. Min Act: -0.1700
Data Index: 1410582 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.5688. Min Act: -0.1700
Data Index: 3760497 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.5376. Min Act: -0.1700
Data Index: 5656193 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.5063. Min Act: -0.1700
Data Index: 7866367 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.5063. Min Act: -0.1700
Data Index: 2330740 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.4751. Min Act: -0.1700
Data Index: 3025882 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.5063. Min Act: -0.1700
Data Index: 353894 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8188. Min Range: -5.8188
Max Act: 5.4751. Min Act: -0.1700
Data Index: 6966937 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19