Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3341 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.2162. Min Act: -0.1700
Data Index: 4603 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.2162. Min Act: -0.1700
Data Index: 2731775 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.1537. Min Act: -0.1700
Data Index: 5929921 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.1225. Min Act: -0.1700
Data Index: 3811738 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.1537. Min Act: -0.1700
Data Index: 4378534 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.1537. Min Act: -0.1700
Data Index: 238172 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.1225. Min Act: -0.1700
Data Index: 1678676 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.1225. Min Act: -0.1700
Data Index: 5497726 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.0600. Min Act: -0.1700
Data Index: 5889281 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.0600. Min Act: -0.1700
Data Index: 4216439 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2162. Min Range: -6.2162
Max Act: 6.0287. Min Act: -0.1700
Data Index: 8181224 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2162. Min Range: -6.2162
Max Act: 5.9975. Min Act: -0.1700
Data Index: 6894904 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2162. Min Range: -6.2162
Max Act: 5.9975. Min Act: -0.1700
Data Index: 4664446 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2162. Min Range: -6.2162
Max Act: 5.9662. Min Act: -0.1700
Data Index: 4797265 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2162. Min Range: -6.2162
Max Act: 5.9662. Min Act: -0.1700
Data Index: 3494682 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2162. Min Range: -6.2162
Max Act: 5.9975. Min Act: -0.1700
Data Index: 1251214 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2162. Min Range: -6.2162
Max Act: 5.9662. Min Act: -0.1700
Data Index: 2012139 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2162. Min Range: -6.2162
Max Act: 5.9350. Min Act: -0.1700
Data Index: 6055103 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2162. Min Range: -6.2162
Max Act: 5.9350. Min Act: -0.1700
Data Index: 433587 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2162. Min Range: -6.2162
Max Act: 5.9350. Min Act: -0.1700
Data Index: 6568842 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19