Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1857 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.7614. Min Act: -0.1700
Data Index: 155107 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.5739. Min Act: -0.1700
Data Index: 6984994 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.3239. Min Act: -0.1700
Data Index: 4581809 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.1989. Min Act: -0.1700
Data Index: 7264647 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.1989. Min Act: -0.1700
Data Index: 4898370 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.1364. Min Act: -0.1700
Data Index: 7768340 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.1364. Min Act: -0.1700
Data Index: 5865437 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.1364. Min Act: -0.1700
Data Index: 309259 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.0739. Min Act: -0.1700
Data Index: 3334353 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.0739. Min Act: -0.1700
Data Index: 3656625 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.0426. Min Act: -0.1700
Data Index: 7276957 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.0739. Min Act: -0.1700
Data Index: 2770341 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.0426. Min Act: -0.1700
Data Index: 5939416 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.0426. Min Act: -0.1700
Data Index: 982478 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7614. Min Range: -5.7614
Max Act: 5.0426. Min Act: -0.1700
Data Index: 4638103 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7614. Min Range: -5.7614
Max Act: 4.9489. Min Act: -0.1700
Data Index: 155108 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7614. Min Range: -5.7614
Max Act: 4.9801. Min Act: -0.1700
Data Index: 7687368 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7614. Min Range: -5.7614
Max Act: 4.9801. Min Act: -0.1700
Data Index: 5101050 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7614. Min Range: -5.7614
Max Act: 4.9801. Min Act: -0.1700
Data Index: 619818 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7614. Min Range: -5.7614
Max Act: 4.9801. Min Act: -0.1700
Data Index: 7394898 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19