Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1882 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.8847. Min Act: -0.1700
Data Index: 2120094 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.8534. Min Act: -0.1700
Data Index: 2369500 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.8221. Min Act: -0.1700
Data Index: 4611144 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.8534. Min Act: -0.1700
Data Index: 2756428 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.8221. Min Act: -0.1700
Data Index: 5975703 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7909. Min Act: -0.1700
Data Index: 3967494 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7909. Min Act: -0.1700
Data Index: 3221077 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7909. Min Act: -0.1700
Data Index: 2120098 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7283. Min Act: -0.1700
Data Index: 3588613 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7283. Min Act: -0.1700
Data Index: 174354 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7596. Min Act: -0.1700
Data Index: 1581351 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7596. Min Act: -0.1700
Data Index: 2299518 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7596. Min Act: -0.1700
Data Index: 4719529 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7596. Min Act: -0.1700
Data Index: 8680323 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7596. Min Act: -0.1700
Data Index: 4303444 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7596. Min Act: -0.1700
Data Index: 4053334 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7596. Min Act: -0.1700
Data Index: 5929573 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7596. Min Act: -0.1700
Data Index: 3740770 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7283. Min Act: -0.1700
Data Index: 3189966 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8847. Min Range: -3.8847
Max Act: 3.7283. Min Act: -0.1700
Data Index: 5017419 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19