Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2055. Min Range: -7.2055
Max Act: 7.2055. Min Act: -0.1700
Data Index: 614139 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2055. Min Range: -7.2055
Max Act: 7.0805. Min Act: -0.1700
Data Index: 8548837 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2055. Min Range: -7.2055
Max Act: 7.0805. Min Act: -0.1700
Data Index: 2718205 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2055. Min Range: -7.2055
Max Act: 7.0805. Min Act: -0.1700
Data Index: 3472049 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2055. Min Range: -7.2055
Max Act: 7.0180. Min Act: -0.1700
Data Index: 7607902 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.9243. Min Act: -0.1700
Data Index: 6594358 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.8930. Min Act: -0.1700
Data Index: 4203247 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.8618. Min Act: -0.1700
Data Index: 3363072 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.7680. Min Act: -0.1700
Data Index: 1617355 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.7368. Min Act: -0.1700
Data Index: 7027325 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.7055. Min Act: -0.1700
Data Index: 4306803 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.7055. Min Act: -0.1700
Data Index: 8766280 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.6743. Min Act: -0.1700
Data Index: 4203248 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.6430. Min Act: -0.1700
Data Index: 2506683 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.6430. Min Act: -0.1700
Data Index: 4551473 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.6430. Min Act: -0.1700
Data Index: 7016290 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.5805. Min Act: -0.1700
Data Index: 2140214 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.5805. Min Act: -0.1700
Data Index: 5606231 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.5493. Min Act: -0.1700
Data Index: 7365159 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2055. Min Range: -7.2055
Max Act: 6.5180. Min Act: -0.1700
Data Index: 970663 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19