Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5846 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.6176. Min Act: -0.1700
Data Index: 3649082 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.4614. Min Act: -0.1700
Data Index: 7487664 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.4301. Min Act: -0.1700
Data Index: 6838636 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.3676. Min Act: -0.1700
Data Index: 6212356 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.2739. Min Act: -0.1700
Data Index: 3457217 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.2426. Min Act: -0.1700
Data Index: 7038153 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.2114. Min Act: -0.1700
Data Index: 8347818 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.2114. Min Act: -0.1700
Data Index: 5838307 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.2114. Min Act: -0.1700
Data Index: 1771017 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.2114. Min Act: -0.1700
Data Index: 8431517 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.1801. Min Act: -0.1700
Data Index: 1778573 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.1801. Min Act: -0.1700
Data Index: 7703269 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.1176. Min Act: -0.1700
Data Index: 5856287 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.1176. Min Act: -0.1700
Data Index: 5592151 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.0239. Min Act: -0.1700
Data Index: 7806656 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.0239. Min Act: -0.1700
Data Index: 6210390 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.0239. Min Act: -0.1700
Data Index: 5677311 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.0239. Min Act: -0.1700
Data Index: 8358231 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.0239. Min Act: -0.1700
Data Index: 4673153 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6176. Min Range: -6.6176
Max Act: 6.0239. Min Act: -0.1700
Data Index: 4009611 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19