Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2273 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.8790. Min Act: -0.1700
Data Index: 6022678 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.7540. Min Act: -0.1700
Data Index: 7638003 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.5978. Min Act: -0.1700
Data Index: 454284 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.6290. Min Act: -0.1700
Data Index: 3777550 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.5353. Min Act: -0.1700
Data Index: 3251699 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.5353. Min Act: -0.1700
Data Index: 3777551 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.4103. Min Act: -0.1700
Data Index: 1288784 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.3478. Min Act: -0.1700
Data Index: 114262 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.3478. Min Act: -0.1700
Data Index: 454287 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.3478. Min Act: -0.1700
Data Index: 5610101 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.3478. Min Act: -0.1700
Data Index: 82213 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.3165. Min Act: -0.1700
Data Index: 7047087 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.3165. Min Act: -0.1700
Data Index: 4166613 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.2853. Min Act: -0.1700
Data Index: 454293 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.2540. Min Act: -0.1700
Data Index: 5163545 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.2228. Min Act: -0.1700
Data Index: 8005234 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.2228. Min Act: -0.1700
Data Index: 8530323 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.1915. Min Act: -0.1700
Data Index: 6228229 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.2228. Min Act: -0.1700
Data Index: 1043053 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8790. Min Range: -6.8790
Max Act: 6.1915. Min Act: -0.1700
Data Index: 721837 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19