Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1210. Min Range: -5.1210
Max Act: 5.1210. Min Act: -0.1700
Data Index: 2431589 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1210. Min Range: -5.1210
Max Act: 5.0585. Min Act: -0.1700
Data Index: 5448956 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1210. Min Range: -5.1210
Max Act: 5.0897. Min Act: -0.1700
Data Index: 950791 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1210. Min Range: -5.1210
Max Act: 5.0272. Min Act: -0.1700
Data Index: 8742192 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1210. Min Range: -5.1210
Max Act: 5.0272. Min Act: -0.1700
Data Index: 7631383 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.8710. Min Act: -0.1700
Data Index: 7977966 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.8085. Min Act: -0.1700
Data Index: 2383786 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.7772. Min Act: -0.1700
Data Index: 5026805 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.7460. Min Act: -0.1700
Data Index: 6031496 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.7460. Min Act: -0.1700
Data Index: 5199155 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.7460. Min Act: -0.1700
Data Index: 5923979 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.7147. Min Act: -0.1700
Data Index: 8024927 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.7147. Min Act: -0.1700
Data Index: 740028 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.7460. Min Act: -0.1700
Data Index: 978364 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.7147. Min Act: -0.1700
Data Index: 2388593 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.6522. Min Act: -0.1700
Data Index: 1054215 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.6522. Min Act: -0.1700
Data Index: 1158018 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.6210. Min Act: -0.1700
Data Index: 1032359 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.6522. Min Act: -0.1700
Data Index: 4520607 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1210. Min Range: -5.1210
Max Act: 4.6522. Min Act: -0.1700
Data Index: 6609059 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19