Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1360 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1330. Min Range: -5.1330
Max Act: 5.1330. Min Act: -0.1700
Data Index: 516922 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.9767. Min Act: -0.1699
Data Index: 5370247 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.9767. Min Act: -0.1700
Data Index: 8811549 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.8830. Min Act: -0.1700
Data Index: 5141340 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.7892. Min Act: -0.1700
Data Index: 183897 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.7580. Min Act: -0.1700
Data Index: 6330549 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.7267. Min Act: -0.1700
Data Index: 5394655 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.7267. Min Act: -0.1700
Data Index: 5062087 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.7267. Min Act: -0.1700
Data Index: 375044 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6955. Min Act: -0.1700
Data Index: 5565312 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6955. Min Act: -0.1700
Data Index: 5853175 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6955. Min Act: -0.1700
Data Index: 8079737 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6955. Min Act: -0.1700
Data Index: 5529011 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6642. Min Act: -0.1700
Data Index: 2926192 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6330. Min Act: -0.1700
Data Index: 8526448 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6330. Min Act: -0.1700
Data Index: 1683171 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6330. Min Act: -0.1700
Data Index: 1316388 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6330. Min Act: -0.1700
Data Index: 674821 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6017. Min Act: -0.1700
Data Index: 126976 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1330. Min Range: -5.1330
Max Act: 4.6017. Min Act: -0.1700
Data Index: 4802195 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19