Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0328. Min Range: -4.0328
Max Act: 4.0328. Min Act: -0.1700
Data Index: 5531439 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0328. Min Range: -4.0328
Max Act: 4.0015. Min Act: -0.1700
Data Index: 7993932 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.9077. Min Act: -0.1700
Data Index: 3739034 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.9390. Min Act: -0.1700
Data Index: 7362720 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.9077. Min Act: -0.1700
Data Index: 7373433 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.9077. Min Act: -0.1700
Data Index: 4432492 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.9077. Min Act: -0.1700
Data Index: 7847497 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.9077. Min Act: -0.1700
Data Index: 1961433 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.9077. Min Act: -0.1700
Data Index: 4894288 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.8764. Min Act: -0.1700
Data Index: 1700922 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.8921. Min Act: -0.1700
Data Index: 6516545 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.8921. Min Act: -0.1700
Data Index: 6304798 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.8921. Min Act: -0.1700
Data Index: 6224699 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.8608. Min Act: -0.1700
Data Index: 6555402 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.8295. Min Act: -0.1700
Data Index: 3261179 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.8295. Min Act: -0.1700
Data Index: 1257012 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.8139. Min Act: -0.1700
Data Index: 3356132 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.8139. Min Act: -0.1700
Data Index: 7279452 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.7983. Min Act: -0.1700
Data Index: 42302 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0328. Min Range: -4.0328
Max Act: 3.7670. Min Act: -0.1700
Data Index: 2500562 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19