Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4198 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.5517. Min Act: -0.1700
Data Index: 3047838 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.5205. Min Act: -0.1700
Data Index: 2030057 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.4267. Min Act: -0.1700
Data Index: 266873 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3955. Min Act: -0.1700
Data Index: 5781136 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3330. Min Act: -0.1700
Data Index: 6594422 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3017. Min Act: -0.1700
Data Index: 1481999 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.3017. Min Act: -0.1700
Data Index: 4360066 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2705. Min Act: -0.1700
Data Index: 4011929 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2705. Min Act: -0.1700
Data Index: 3625703 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2080. Min Act: -0.1700
Data Index: 617485 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2392. Min Act: -0.1700
Data Index: 5255981 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2080. Min Act: -0.1700
Data Index: 4175684 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.1767. Min Act: -0.1700
Data Index: 949212 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.2080. Min Act: -0.1700
Data Index: 2413575 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.1767. Min Act: -0.1700
Data Index: 8731942 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.1455. Min Act: -0.1700
Data Index: 4652042 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.1142. Min Act: -0.1700
Data Index: 871038 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.1142. Min Act: -0.1700
Data Index: 2979348 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.1142. Min Act: -0.1700
Data Index: 2243024 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5517. Min Range: -6.5517
Max Act: 6.0830. Min Act: -0.1700
Data Index: 5372600 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19