Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0085. Min Range: -7.0085
Max Act: 7.0085. Min Act: -0.1700
Data Index: 7489579 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.7273. Min Act: -0.1700
Data Index: 7749588 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.5710. Min Act: -0.1700
Data Index: 5032437 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.5710. Min Act: -0.1700
Data Index: 742336 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.4773. Min Act: -0.1700
Data Index: 4308110 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.5085. Min Act: -0.1700
Data Index: 528704 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.4773. Min Act: -0.1700
Data Index: 704070 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.4460. Min Act: -0.1700
Data Index: 7992786 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.4460. Min Act: -0.1700
Data Index: 4138688 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.4460. Min Act: -0.1700
Data Index: 4278727 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.4148. Min Act: -0.1700
Data Index: 3237460 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.3835. Min Act: -0.1700
Data Index: 6523805 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.3835. Min Act: -0.1700
Data Index: 1891469 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.3210. Min Act: -0.1700
Data Index: 339279 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.2585. Min Act: -0.1700
Data Index: 4416094 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.2585. Min Act: -0.1700
Data Index: 3039408 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.1960. Min Act: -0.1700
Data Index: 859638 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.2273. Min Act: -0.1700
Data Index: 6317137 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.1960. Min Act: -0.1700
Data Index: 2094484 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0085. Min Range: -7.0085
Max Act: 6.1960. Min Act: -0.1700
Data Index: 5625339 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19