Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2858. Min Range: -4.2858
Max Act: 4.2858. Min Act: -0.1700
Data Index: 437259 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2858. Min Range: -4.2858
Max Act: 4.1921. Min Act: -0.1700
Data Index: 7798519 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2858. Min Range: -4.2858
Max Act: 4.1296. Min Act: -0.1700
Data Index: 7160700 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2858. Min Range: -4.2858
Max Act: 4.0670. Min Act: -0.1700
Data Index: 3452320 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2858. Min Range: -4.2858
Max Act: 4.0983. Min Act: -0.1700
Data Index: 7074929 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2858. Min Range: -4.2858
Max Act: 4.0670. Min Act: -0.1700
Data Index: 6889495 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2858. Min Range: -4.2858
Max Act: 4.0358. Min Act: -0.1700
Data Index: 2378857 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2858. Min Range: -4.2858
Max Act: 4.0670. Min Act: -0.1700
Data Index: 2393438 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2858. Min Range: -4.2858
Max Act: 4.0358. Min Act: -0.1700
Data Index: 2838060 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9733. Min Act: -0.1700
Data Index: 4305118 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9733. Min Act: -0.1700
Data Index: 7949965 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9420. Min Act: -0.1700
Data Index: 1055665 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9733. Min Act: -0.1700
Data Index: 1996148 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9420. Min Act: -0.1700
Data Index: 4395800 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9420. Min Act: -0.1700
Data Index: 763084 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9107. Min Act: -0.1700
Data Index: 4128343 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9733. Min Act: -0.1700
Data Index: 3111619 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9420. Min Act: -0.1700
Data Index: 3375762 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9107. Min Act: -0.1700
Data Index: 5691816 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2858. Min Range: -4.2858
Max Act: 3.9107. Min Act: -0.1700
Data Index: 6510482 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19