Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0016. Min Range: -5.0016
Max Act: 5.0016. Min Act: -0.1700
Data Index: 5364347 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.9703. Min Act: -0.1700
Data Index: 8821979 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.8766. Min Act: -0.1700
Data Index: 243797 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.8766. Min Act: -0.1700
Data Index: 4800412 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.9078. Min Act: -0.1700
Data Index: 1065735 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.8766. Min Act: -0.1700
Data Index: 7610467 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.8453. Min Act: -0.1700
Data Index: 7822937 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.8453. Min Act: -0.1700
Data Index: 1021355 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.8141. Min Act: -0.1700
Data Index: 4368348 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.7828. Min Act: -0.1700
Data Index: 2883749 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.7203. Min Act: -0.1700
Data Index: 8499010 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.7203. Min Act: -0.1700
Data Index: 6037069 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.7203. Min Act: -0.1700
Data Index: 324364 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.7203. Min Act: -0.1700
Data Index: 3172515 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.6891. Min Act: -0.1700
Data Index: 4917235 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.6891. Min Act: -0.1700
Data Index: 513757 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.6578. Min Act: -0.1700
Data Index: 7717883 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.6578. Min Act: -0.1700
Data Index: 8147212 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.6266. Min Act: -0.1700
Data Index: 188980 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0016. Min Range: -5.0016
Max Act: 4.6266. Min Act: -0.1700
Data Index: 5993611 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19