Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4555 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1028. Min Range: -6.1028
Max Act: 6.1028. Min Act: -0.1700
Data Index: 712969 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.9466. Min Act: -0.1700
Data Index: 3450226 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.7591. Min Act: -0.1700
Data Index: 4354917 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.6653. Min Act: -0.1700
Data Index: 5513252 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.5716. Min Act: -0.1700
Data Index: 2605141 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.5716. Min Act: -0.1700
Data Index: 5508545 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.4466. Min Act: -0.1700
Data Index: 1294169 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.4153. Min Act: -0.1700
Data Index: 8757450 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.4153. Min Act: -0.1700
Data Index: 3246527 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.3841. Min Act: -0.1700
Data Index: 8713019 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.3528. Min Act: -0.1700
Data Index: 7815716 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.3528. Min Act: -0.1700
Data Index: 2146078 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.3216. Min Act: -0.1700
Data Index: 7181695 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.3216. Min Act: -0.1700
Data Index: 723424 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.3216. Min Act: -0.1700
Data Index: 4419704 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.2903. Min Act: -0.1700
Data Index: 4649136 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.2903. Min Act: -0.1700
Data Index: 7542867 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.2903. Min Act: -0.1700
Data Index: 7878305 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.2903. Min Act: -0.1700
Data Index: 8470398 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1028. Min Range: -6.1028
Max Act: 5.2903. Min Act: -0.1700
Data Index: 7693441 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19