Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.7235. Min Act: -0.1700
Data Index: 1833281 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.7391. Min Act: -0.1700
Data Index: 113224 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.6453. Min Act: -0.1700
Data Index: 1336851 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.6453. Min Act: -0.1700
Data Index: 7440152 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5983. Min Act: -0.1700
Data Index: 1550580 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5670. Min Act: -0.1700
Data Index: 5285254 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5357. Min Act: -0.1700
Data Index: 3641197 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5357. Min Act: -0.1700
Data Index: 5104293 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5514. Min Act: -0.1700
Data Index: 1602892 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5201. Min Act: -0.1700
Data Index: 5259872 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5201. Min Act: -0.1700
Data Index: 4069198 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5357. Min Act: -0.1700
Data Index: 5076414 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5044. Min Act: -0.1700
Data Index: 1335047 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5201. Min Act: -0.1700
Data Index: 476376 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5044. Min Act: -0.1700
Data Index: 6346126 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5044. Min Act: -0.1700
Data Index: 8337927 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.5044. Min Act: -0.1700
Data Index: 897812 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.4887. Min Act: -0.1700
Data Index: 5195640 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.4887. Min Act: -0.1700
Data Index: 76173 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7391. Min Range: -3.7391
Max Act: 3.4887. Min Act: -0.1700
Data Index: 5259874 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19