Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.3546. Min Act: -0.1700
Data Index: 6274383 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.3233. Min Act: -0.1700
Data Index: 4279887 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.3233. Min Act: -0.1700
Data Index: 1886515 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2296. Min Act: -0.1700
Data Index: 5584720 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2921. Min Act: -0.1700
Data Index: 2725414 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2608. Min Act: -0.1700
Data Index: 1512807 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2921. Min Act: -0.1700
Data Index: 3868787 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2608. Min Act: -0.1700
Data Index: 341025 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2921. Min Act: -0.1700
Data Index: 6204720 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2608. Min Act: -0.1700
Data Index: 8694479 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2296. Min Act: -0.1700
Data Index: 784690 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2296. Min Act: -0.1700
Data Index: 1886499 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2608. Min Act: -0.1700
Data Index: 341054 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2608. Min Act: -0.1700
Data Index: 4754061 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2608. Min Act: -0.1700
Data Index: 1861870 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.1983. Min Act: -0.1700
Data Index: 1055502 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.1983. Min Act: -0.1700
Data Index: 7450733 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.2296. Min Act: -0.1700
Data Index: 341065 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.1671. Min Act: -0.1700
Data Index: 341063 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3546. Min Range: -4.3546
Max Act: 4.1983. Min Act: -0.1700
Data Index: 8240054 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19