Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3201 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0630. Min Range: -9.0630
Max Act: 9.0630. Min Act: -0.1700
Data Index: 5609036 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0630. Min Range: -9.0630
Max Act: 8.7505. Min Act: -0.1700
Data Index: 3322285 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0630. Min Range: -9.0630
Max Act: 8.6255. Min Act: -0.1700
Data Index: 2532037 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0630. Min Range: -9.0630
Max Act: 8.5630. Min Act: -0.1700
Data Index: 8285770 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0630. Min Range: -9.0630
Max Act: 8.3755. Min Act: -0.1700
Data Index: 448212 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0630. Min Range: -9.0630
Max Act: 8.2505. Min Act: -0.1700
Data Index: 2680308 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0630. Min Range: -9.0630
Max Act: 8.2505. Min Act: -0.1700
Data Index: 4194650 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0630. Min Range: -9.0630
Max Act: 8.0630. Min Act: -0.1700
Data Index: 2841657 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0630. Min Range: -9.0630
Max Act: 8.0317. Min Act: -0.1700
Data Index: 4194649 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.8130. Min Act: -0.1700
Data Index: 156006 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.8442. Min Act: -0.1700
Data Index: 2706691 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.8130. Min Act: -0.1700
Data Index: 490122 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.7505. Min Act: -0.1700
Data Index: 8546378 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.8130. Min Act: -0.1700
Data Index: 4013661 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.7817. Min Act: -0.1700
Data Index: 3292261 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.7192. Min Act: -0.1700
Data Index: 108763 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.7505. Min Act: -0.1700
Data Index: 3884190 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.7192. Min Act: -0.1700
Data Index: 4335118 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.7192. Min Act: -0.1700
Data Index: 2362309 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0630. Min Range: -9.0630
Max Act: 7.6567. Min Act: -0.1700
Data Index: 1288863 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19