Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5656 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.8345. Min Act: -0.1700
Data Index: 4471579 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.5845. Min Act: -0.1700
Data Index: 7959140 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.4908. Min Act: -0.1700
Data Index: 8264291 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.4595. Min Act: -0.1700
Data Index: 180842 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.4595. Min Act: -0.1700
Data Index: 8282863 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.4283. Min Act: -0.1700
Data Index: 5290226 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.4283. Min Act: -0.1700
Data Index: 7338441 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.3345. Min Act: -0.1700
Data Index: 1693192 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.3345. Min Act: -0.1700
Data Index: 4231077 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.3658. Min Act: -0.1700
Data Index: 3308753 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.3033. Min Act: -0.1700
Data Index: 5832743 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.3033. Min Act: -0.1700
Data Index: 2195773 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.3033. Min Act: -0.1700
Data Index: 7166105 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.3345. Min Act: -0.1700
Data Index: 891078 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.3033. Min Act: -0.1700
Data Index: 1882119 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.3033. Min Act: -0.1700
Data Index: 1232951 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.2720. Min Act: -0.1700
Data Index: 3785843 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.2408. Min Act: -0.1700
Data Index: 3595113 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.2720. Min Act: -0.1700
Data Index: 347268 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8345. Min Range: -7.8345
Max Act: 7.2408. Min Act: -0.1700
Data Index: 1783014 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19