Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4794 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.7004. Min Act: -0.1700
Data Index: 2228710 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.5442. Min Act: -0.1700
Data Index: 6231508 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.5442. Min Act: -0.1700
Data Index: 6231510 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.5442. Min Act: -0.1700
Data Index: 6098141 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.5129. Min Act: -0.1700
Data Index: 5496707 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4504. Min Act: -0.1700
Data Index: 7513052 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4817. Min Act: -0.1700
Data Index: 1885630 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4504. Min Act: -0.1700
Data Index: 1548031 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4504. Min Act: -0.1700
Data Index: 8170177 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4192. Min Act: -0.1700
Data Index: 3449087 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4504. Min Act: -0.1700
Data Index: 6969472 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4192. Min Act: -0.1700
Data Index: 8532578 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4192. Min Act: -0.1700
Data Index: 142504 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4192. Min Act: -0.1700
Data Index: 7863533 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4192. Min Act: -0.1700
Data Index: 3846269 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.4192. Min Act: -0.1700
Data Index: 4114292 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.3879. Min Act: -0.1699
Data Index: 1804005 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.3879. Min Act: -0.1700
Data Index: 3793540 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.3879. Min Act: -0.1700
Data Index: 1931868 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7004. Min Range: -6.7004
Max Act: 6.3879. Min Act: -0.1700
Data Index: 5546434 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19