Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4377 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0072. Min Range: -7.0072
Max Act: 7.0072. Min Act: -0.1700
Data Index: 2702172 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.9760. Min Act: -0.1700
Data Index: 7958456 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.8510. Min Act: -0.1700
Data Index: 7619290 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.8197. Min Act: -0.1700
Data Index: 3394585 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.8197. Min Act: -0.1700
Data Index: 8483588 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.8197. Min Act: -0.1700
Data Index: 5298933 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.7572. Min Act: -0.1700
Data Index: 3639684 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.6947. Min Act: -0.1700
Data Index: 4515648 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.7885. Min Act: -0.1700
Data Index: 5601317 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.7260. Min Act: -0.1700
Data Index: 3108014 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.6947. Min Act: -0.1700
Data Index: 7086102 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.7260. Min Act: -0.1700
Data Index: 1355909 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.7260. Min Act: -0.1700
Data Index: 100004 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.6635. Min Act: -0.1700
Data Index: 1166473 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.6635. Min Act: -0.1700
Data Index: 434388 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.6635. Min Act: -0.1700
Data Index: 2281652 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.6322. Min Act: -0.1700
Data Index: 3048750 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.6322. Min Act: -0.1700
Data Index: 7930691 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.6010. Min Act: -0.1700
Data Index: 3150106 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0072. Min Range: -7.0072
Max Act: 6.6010. Min Act: -0.1700
Data Index: 6374942 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19