Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2209 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.8258. Min Act: -0.1700
Data Index: 8771511 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.7008. Min Act: -0.1700
Data Index: 6118967 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.6383. Min Act: -0.1700
Data Index: 7031581 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.6070. Min Act: -0.1700
Data Index: 1822246 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.6070. Min Act: -0.1700
Data Index: 6007215 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.6070. Min Act: -0.1700
Data Index: 8566274 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.5758. Min Act: -0.1700
Data Index: 4274255 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.5758. Min Act: -0.1700
Data Index: 260338 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.5445. Min Act: -0.1700
Data Index: 5014006 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.5133. Min Act: -0.1700
Data Index: 7232408 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.5133. Min Act: -0.1700
Data Index: 5046396 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.5133. Min Act: -0.1700
Data Index: 7062121 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.5133. Min Act: -0.1700
Data Index: 1985338 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.4820. Min Act: -0.1700
Data Index: 8361897 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.4820. Min Act: -0.1700
Data Index: 5165002 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.4820. Min Act: -0.1700
Data Index: 5284965 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.4195. Min Act: -0.1700
Data Index: 4866516 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.4508. Min Act: -0.1700
Data Index: 3466256 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.4508. Min Act: -0.1700
Data Index: 8617594 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8258. Min Range: -5.8258
Max Act: 5.4508. Min Act: -0.1700
Data Index: 1446029 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19