Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3269 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7630. Min Range: -9.7630
Max Act: 9.7630. Min Act: -0.1700
Data Index: 996665 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7630. Min Range: -9.7630
Max Act: 9.6380. Min Act: -0.1700
Data Index: 5733682 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7630. Min Range: -9.7630
Max Act: 9.2630. Min Act: -0.1700
Data Index: 8582499 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7630. Min Range: -9.7630
Max Act: 9.0755. Min Act: -0.1700
Data Index: 5418897 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7630. Min Range: -9.7630
Max Act: 9.0130. Min Act: -0.1700
Data Index: 560524 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.9505. Min Act: -0.1700
Data Index: 2680575 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7630. Min Range: -9.7630
Max Act: 9.0130. Min Act: -0.1700
Data Index: 3657030 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7630. Min Range: -9.7630
Max Act: 9.0130. Min Act: -0.1700
Data Index: 8678353 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.9505. Min Act: -0.1700
Data Index: 7119950 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.9505. Min Act: -0.1700
Data Index: 2353780 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.9505. Min Act: -0.1700
Data Index: 5275642 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.9505. Min Act: -0.1700
Data Index: 416941 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.9505. Min Act: -0.1700
Data Index: 3577853 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.9505. Min Act: -0.1700
Data Index: 4486017 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.8880. Min Act: -0.1700
Data Index: 7226562 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.8880. Min Act: -0.1700
Data Index: 5561323 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.8255. Min Act: -0.1700
Data Index: 1665227 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.8255. Min Act: -0.1700
Data Index: 3213056 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.8255. Min Act: -0.1700
Data Index: 2007776 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7630. Min Range: -9.7630
Max Act: 8.8255. Min Act: -0.1700
Data Index: 2132892 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19