Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.9814. Min Act: -0.1700
Data Index: 2108303 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.9502. Min Act: -0.1700
Data Index: 7335537 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.9189. Min Act: -0.1700
Data Index: 3441155 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.9189. Min Act: -0.1700
Data Index: 5077923 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.7314. Min Act: -0.1700
Data Index: 4269317 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.7314. Min Act: -0.1700
Data Index: 3645601 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.7002. Min Act: -0.1700
Data Index: 1960504 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.7002. Min Act: -0.1700
Data Index: 3444965 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.7002. Min Act: -0.1700
Data Index: 517956 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.6689. Min Act: -0.1700
Data Index: 2278107 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.7002. Min Act: -0.1700
Data Index: 3941371 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.7002. Min Act: -0.1700
Data Index: 3518622 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.6689. Min Act: -0.1700
Data Index: 3780619 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.6377. Min Act: -0.1700
Data Index: 4445795 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.6377. Min Act: -0.1700
Data Index: 7239908 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.6377. Min Act: -0.1700
Data Index: 7934598 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.6064. Min Act: -0.1700
Data Index: 2641058 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.6377. Min Act: -0.1700
Data Index: 2294492 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.6064. Min Act: -0.1700
Data Index: 6636287 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9814. Min Range: -6.9814
Max Act: 6.6064. Min Act: -0.1700
Data Index: 4232437 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19