Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6472. Min Range: -10.6472
Max Act: 10.6472. Min Act: -0.1700
Data Index: 5713891 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6472. Min Range: -10.6472
Max Act: 10.5222. Min Act: -0.1700
Data Index: 2617671 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6472. Min Range: -10.6472
Max Act: 10.4597. Min Act: -0.1700
Data Index: 3269840 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6472. Min Range: -10.6472
Max Act: 10.2097. Min Act: -0.1700
Data Index: 8015835 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6472. Min Range: -10.6472
Max Act: 10.1472. Min Act: -0.1700
Data Index: 5392330 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6472. Min Range: -10.6472
Max Act: 10.0847. Min Act: -0.1700
Data Index: 4671973 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6472. Min Range: -10.6472
Max Act: 10.0222. Min Act: -0.1700
Data Index: 2606059 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.9597. Min Act: -0.1700
Data Index: 7779759 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.9597. Min Act: -0.1700
Data Index: 6609130 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.8972. Min Act: -0.1700
Data Index: 5713892 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.7722. Min Act: -0.1700
Data Index: 3003139 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.7722. Min Act: -0.1700
Data Index: 4585967 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.7722. Min Act: -0.1700
Data Index: 6671632 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.7097. Min Act: -0.1700
Data Index: 7619437 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.6472. Min Act: -0.1700
Data Index: 4687770 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.5847. Min Act: -0.1700
Data Index: 358116 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.5222. Min Act: -0.1700
Data Index: 2944546 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.5847. Min Act: -0.1700
Data Index: 4314002 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.5847. Min Act: -0.1700
Data Index: 1219884 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6472. Min Range: -10.6472
Max Act: 9.5847. Min Act: -0.1700
Data Index: 5512284 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19