Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2914. Min Range: -7.2914
Max Act: 7.2914. Min Act: -0.1700
Data Index: 42158 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2914. Min Range: -7.2914
Max Act: 7.0726. Min Act: -0.1700
Data Index: 1861518 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2914. Min Range: -7.2914
Max Act: 7.0414. Min Act: -0.1700
Data Index: 4096509 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2914. Min Range: -7.2914
Max Act: 7.0101. Min Act: -0.1700
Data Index: 4776443 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.9789. Min Act: -0.1700
Data Index: 5765710 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.9476. Min Act: -0.1700
Data Index: 1597386 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.9164. Min Act: -0.1700
Data Index: 8240818 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.8226. Min Act: -0.1700
Data Index: 7458122 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.8851. Min Act: -0.1700
Data Index: 8295157 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.8539. Min Act: -0.1700
Data Index: 4908780 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.8539. Min Act: -0.1700
Data Index: 1018389 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.8226. Min Act: -0.1700
Data Index: 895815 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.8539. Min Act: -0.1700
Data Index: 3883873 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.7914. Min Act: -0.1700
Data Index: 1045071 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.7914. Min Act: -0.1700
Data Index: 3315044 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.7914. Min Act: -0.1700
Data Index: 4243404 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.7601. Min Act: -0.1700
Data Index: 5390205 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.7601. Min Act: -0.1700
Data Index: 8820993 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.7601. Min Act: -0.1700
Data Index: 6645777 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2914. Min Range: -7.2914
Max Act: 6.6976. Min Act: -0.1700
Data Index: 7925376 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19