Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.4097. Min Act: -0.1700
Data Index: 7036220 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.3472. Min Act: -0.1700
Data Index: 1539846 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4097. Min Range: -8.4097
Max Act: 8.2847. Min Act: -0.1700
Data Index: 3033351 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.9097. Min Act: -0.1700
Data Index: 1403723 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.8785. Min Act: -0.1700
Data Index: 3347622 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.8160. Min Act: -0.1700
Data Index: 1119271 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.7535. Min Act: -0.1700
Data Index: 5316640 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.7222. Min Act: -0.1700
Data Index: 2445398 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.6910. Min Act: -0.1700
Data Index: 8203929 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.6910. Min Act: -0.1700
Data Index: 5896443 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.6597. Min Act: -0.1700
Data Index: 6306603 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.5972. Min Act: -0.1700
Data Index: 4390366 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.5035. Min Act: -0.1700
Data Index: 2149542 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.5035. Min Act: -0.1700
Data Index: 727145 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.5035. Min Act: -0.1700
Data Index: 433540 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.4722. Min Act: -0.1700
Data Index: 725821 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.4410. Min Act: -0.1700
Data Index: 48142 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.4722. Min Act: -0.1700
Data Index: 5547807 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.4410. Min Act: -0.1700
Data Index: 2468479 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4097. Min Range: -8.4097
Max Act: 7.4722. Min Act: -0.1700
Data Index: 5778810 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19