Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1166 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1551. Min Range: -6.1551
Max Act: 6.1551. Min Act: -0.1700
Data Index: 5278445 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1551. Min Range: -6.1551
Max Act: 6.0614. Min Act: -0.1700
Data Index: 2046558 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.9989. Min Act: -0.1700
Data Index: 5278446 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8426. Min Act: -0.1700
Data Index: 7841893 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8739. Min Act: -0.1700
Data Index: 5278453 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 3004773 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8739. Min Act: -0.1700
Data Index: 3398210 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8739. Min Act: -0.1697
Data Index: 5068144 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 2916526 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8426. Min Act: -0.1700
Data Index: 5546318 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 5278452 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 1267917 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 5278460 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.8114. Min Act: -0.1700
Data Index: 1937949 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7801. Min Act: -0.1700
Data Index: 626927 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7176. Min Act: -0.1700
Data Index: 138504 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5295621 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 3885789 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 4843116 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1551. Min Range: -6.1551
Max Act: 5.7489. Min Act: -0.1700
Data Index: 1562589 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19