Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.8091. Min Act: -0.1700
Data Index: 8482802 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.4028. Min Act: -0.1700
Data Index: 4257160 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.3403. Min Act: -0.1700
Data Index: 5612237 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.3403. Min Act: -0.1700
Data Index: 7818817 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.3091. Min Act: -0.1700
Data Index: 191490 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.2778. Min Act: -0.1700
Data Index: 1896700 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.2778. Min Act: -0.1700
Data Index: 2480398 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.2466. Min Act: -0.1700
Data Index: 6065064 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.2153. Min Act: -0.1700
Data Index: 3784463 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.2153. Min Act: -0.1700
Data Index: 1030090 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.1841. Min Act: -0.1700
Data Index: 536287 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.1841. Min Act: -0.1700
Data Index: 3834426 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.1528. Min Act: -0.1700
Data Index: 6037929 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.1528. Min Act: -0.1700
Data Index: 5117393 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.1216. Min Act: -0.1700
Data Index: 4521161 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.1216. Min Act: -0.1700
Data Index: 7790971 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.0903. Min Act: -0.1700
Data Index: 3484248 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.0903. Min Act: -0.1700
Data Index: 3097826 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.0903. Min Act: -0.1700
Data Index: 2647616 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8091. Min Range: -6.8091
Max Act: 6.0903. Min Act: -0.1700
Data Index: 2490746 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19