Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 877 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.9128. Min Act: -0.1700
Data Index: 4806757 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.7878. Min Act: -0.1700
Data Index: 5267789 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.6003. Min Act: -0.1700
Data Index: 7796618 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.5378. Min Act: -0.1700
Data Index: 622279 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.3503. Min Act: -0.1700
Data Index: 4437763 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.2878. Min Act: -0.1700
Data Index: 497376 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.2253. Min Act: -0.1700
Data Index: 2278914 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.2253. Min Act: -0.1700
Data Index: 5209385 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.2253. Min Act: -0.1700
Data Index: 2653502 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.1628. Min Act: -0.1700
Data Index: 6339631 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.1003. Min Act: -0.1700
Data Index: 1044036 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.1628. Min Act: -0.1700
Data Index: 7698097 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.1003. Min Act: -0.1700
Data Index: 6761419 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.1003. Min Act: -0.1700
Data Index: 2977205 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.0378. Min Act: -0.1700
Data Index: 8201904 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.0378. Min Act: -0.1700
Data Index: 8830887 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.0378. Min Act: -0.1700
Data Index: 6738652 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9128. Min Range: -9.9128
Max Act: 9.0378. Min Act: -0.1700
Data Index: 2875353 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9128. Min Range: -9.9128
Max Act: 8.9753. Min Act: -0.1700
Data Index: 136405 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9128. Min Range: -9.9128
Max Act: 8.9753. Min Act: -0.1700
Data Index: 5109215 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19