Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0744. Min Range: -6.0744
Max Act: 6.0744. Min Act: -0.1700
Data Index: 5480076 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.8869. Min Act: -0.1700
Data Index: 4056224 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.8244. Min Act: -0.1700
Data Index: 6195896 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.8244. Min Act: -0.1700
Data Index: 7172924 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.7931. Min Act: -0.1700
Data Index: 3668138 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.7931. Min Act: -0.1700
Data Index: 703417 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.7619. Min Act: -0.1700
Data Index: 1164174 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.7306. Min Act: -0.1700
Data Index: 5632741 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6994. Min Act: -0.1700
Data Index: 6610174 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6994. Min Act: -0.1700
Data Index: 4357970 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6994. Min Act: -0.1700
Data Index: 2674277 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6681. Min Act: -0.1700
Data Index: 410816 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6681. Min Act: -0.1700
Data Index: 8048554 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6681. Min Act: -0.1700
Data Index: 8729516 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6681. Min Act: -0.1700
Data Index: 6389507 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6056. Min Act: -0.1700
Data Index: 7450177 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6369. Min Act: -0.1700
Data Index: 7554175 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6056. Min Act: -0.1700
Data Index: 3398790 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6056. Min Act: -0.1700
Data Index: 594001 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0744. Min Range: -6.0744
Max Act: 5.6056. Min Act: -0.1700
Data Index: 1910765 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19