Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4167 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3043. Min Range: -6.3043
Max Act: 6.3043. Min Act: -0.1700
Data Index: 490269 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3043. Min Range: -6.3043
Max Act: 6.2418. Min Act: -0.1700
Data Index: 4798238 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3043. Min Range: -6.3043
Max Act: 6.2105. Min Act: -0.1700
Data Index: 7533848 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.9918. Min Act: -0.1700
Data Index: 1651012 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.9918. Min Act: -0.1700
Data Index: 3562976 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.9605. Min Act: -0.1700
Data Index: 4542924 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.9293. Min Act: -0.1700
Data Index: 6791830 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.9293. Min Act: -0.1700
Data Index: 5615341 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.8668. Min Act: -0.1700
Data Index: 775519 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.8668. Min Act: -0.1700
Data Index: 2445352 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.8668. Min Act: -0.1700
Data Index: 7091566 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.8043. Min Act: -0.1700
Data Index: 2111396 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.7730. Min Act: -0.1700
Data Index: 4760265 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.7730. Min Act: -0.1700
Data Index: 5399725 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.7418. Min Act: -0.1700
Data Index: 858910 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.7105. Min Act: -0.1700
Data Index: 1201153 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.7105. Min Act: -0.1700
Data Index: 866080 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.7105. Min Act: -0.1700
Data Index: 7271902 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.7105. Min Act: -0.1700
Data Index: 162263 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3043. Min Range: -6.3043
Max Act: 5.7105. Min Act: -0.1700
Data Index: 5507051 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19