Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.1988. Min Act: -0.1700
Data Index: 4950994 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0426. Min Act: -0.1700
Data Index: 4669506 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0113. Min Act: -0.1700
Data Index: 4960668 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1988. Min Range: -5.1988
Max Act: 5.0113. Min Act: -0.1700
Data Index: 1317493 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.9801. Min Act: -0.1700
Data Index: 8159325 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.8863. Min Act: -0.1700
Data Index: 3829129 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.8863. Min Act: -0.1700
Data Index: 7279586 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.8863. Min Act: -0.1700
Data Index: 7709421 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.8551. Min Act: -0.1700
Data Index: 3634256 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.8238. Min Act: -0.1700
Data Index: 2208486 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.8238. Min Act: -0.1700
Data Index: 7709420 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.7613. Min Act: -0.1700
Data Index: 8751359 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.7926. Min Act: -0.1700
Data Index: 5612040 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.7926. Min Act: -0.1700
Data Index: 6876134 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.7301. Min Act: -0.1700
Data Index: 1803097 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.7301. Min Act: -0.1700
Data Index: 3926470 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.7301. Min Act: -0.1700
Data Index: 6736318 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.6676. Min Act: -0.1700
Data Index: 3554541 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.6988. Min Act: -0.1700
Data Index: 4261763 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1988. Min Range: -5.1988
Max Act: 4.6988. Min Act: -0.1700
Data Index: 4327178 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19