Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0299. Min Range: -9.0299
Max Act: 9.0299. Min Act: -0.1700
Data Index: 2188608 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.7174. Min Act: -0.1700
Data Index: 313619 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.6549. Min Act: -0.1700
Data Index: 1452321 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.6549. Min Act: -0.1700
Data Index: 2344458 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.4049. Min Act: -0.1700
Data Index: 6708893 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.4674. Min Act: -0.1700
Data Index: 3594677 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.4674. Min Act: -0.1700
Data Index: 432360 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.4049. Min Act: -0.1700
Data Index: 4710826 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.4049. Min Act: -0.1700
Data Index: 4514719 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.3424. Min Act: -0.1700
Data Index: 8060299 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.3424. Min Act: -0.1700
Data Index: 241182 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.3424. Min Act: -0.1700
Data Index: 5000134 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.3424. Min Act: -0.1700
Data Index: 3505035 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.2799. Min Act: -0.1700
Data Index: 8493852 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.1549. Min Act: -0.1700
Data Index: 1881038 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.1549. Min Act: -0.1700
Data Index: 6120049 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.1549. Min Act: -0.1700
Data Index: 8692513 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.0924. Min Act: -0.1700
Data Index: 4266130 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.1549. Min Act: -0.1700
Data Index: 1180254 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0299. Min Range: -9.0299
Max Act: 8.1549. Min Act: -0.1700
Data Index: 4523821 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19