Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2932 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1864. Min Range: -9.1864
Max Act: 9.1864. Min Act: -0.1700
Data Index: 3998124 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1864. Min Range: -9.1864
Max Act: 9.1864. Min Act: -0.1700
Data Index: 6143350 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1864. Min Range: -9.1864
Max Act: 9.0614. Min Act: -0.1700
Data Index: 545469 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.9989. Min Act: -0.1700
Data Index: 7543305 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.9989. Min Act: -0.1700
Data Index: 5650324 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.9364. Min Act: -0.1700
Data Index: 3998125 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.8114. Min Act: -0.1700
Data Index: 5871684 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.7489. Min Act: -0.1700
Data Index: 87322 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.6864. Min Act: -0.1700
Data Index: 1226713 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.6864. Min Act: -0.1700
Data Index: 4013402 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.6864. Min Act: -0.1700
Data Index: 6466592 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.6864. Min Act: -0.1700
Data Index: 5871682 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.6864. Min Act: -0.1700
Data Index: 3881034 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.6239. Min Act: -0.1700
Data Index: 3324041 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.6239. Min Act: -0.1700
Data Index: 788286 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.6239. Min Act: -0.1700
Data Index: 5089299 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.6239. Min Act: -0.1700
Data Index: 517309 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.5614. Min Act: -0.1700
Data Index: 2337631 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.5614. Min Act: -0.1700
Data Index: 2452792 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1864. Min Range: -9.1864
Max Act: 8.5614. Min Act: -0.1700
Data Index: 3865238 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19