Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5920 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.7227. Min Act: -0.1700
Data Index: 2913512 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.6586. Min Act: -0.1700
Data Index: 5842506 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.6586. Min Act: -0.1700
Data Index: 1182748 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.6426. Min Act: -0.1700
Data Index: 5416296 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.6265. Min Act: -0.1700
Data Index: 1121722 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.6104. Min Act: -0.1700
Data Index: 1688934 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.6104. Min Act: -0.1700
Data Index: 1683057 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5943. Min Act: -0.1700
Data Index: 3376189 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5943. Min Act: -0.1700
Data Index: 5716401 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5943. Min Act: -0.1700
Data Index: 2706508 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5782. Min Act: -0.1700
Data Index: 6314837 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5460. Min Act: -0.1700
Data Index: 8326534 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5621. Min Act: -0.1700
Data Index: 4990788 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5460. Min Act: -0.1700
Data Index: 5307558 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5298. Min Act: -0.1700
Data Index: 712332 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5460. Min Act: -0.1700
Data Index: 1688941 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.4974. Min Act: -0.1700
Data Index: 943254 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.4974. Min Act: -0.1700
Data Index: 4482944 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.4974. Min Act: -0.1700
Data Index: 4779127 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7227. Min Range: -2.7227
Max Act: 2.5136. Min Act: -0.1700
Data Index: 5186914 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19