Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.7083. Min Act: -0.1700
Data Index: 3018387 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.6770. Min Act: -0.1700
Data Index: 1326791 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.3958. Min Act: -0.1700
Data Index: 3095788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.3958. Min Act: -0.1700
Data Index: 1192378 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.3645. Min Act: -0.1700
Data Index: 1574448 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.3333. Min Act: -0.1700
Data Index: 1810704 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.3020. Min Act: -0.1700
Data Index: 1395567 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.3333. Min Act: -0.1700
Data Index: 4178491 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.3020. Min Act: -0.1700
Data Index: 2974409 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.2708. Min Act: -0.1700
Data Index: 138307 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.2395. Min Act: -0.1700
Data Index: 6775552 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.2395. Min Act: -0.1700
Data Index: 3270446 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.2083. Min Act: -0.1700
Data Index: 1417876 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.2083. Min Act: -0.1700
Data Index: 7399562 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.2083. Min Act: -0.1700
Data Index: 2812641 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.2083. Min Act: -0.1700
Data Index: 2631985 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.2083. Min Act: -0.1700
Data Index: 7909321 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.1770. Min Act: -0.1700
Data Index: 5067021 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.1770. Min Act: -0.1700
Data Index: 6715544 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7083. Min Range: -6.7083
Max Act: 6.1770. Min Act: -0.1700
Data Index: 6715915 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19