Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5714 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.2315. Min Act: -0.1700
Data Index: 2212042 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.1377. Min Act: -0.1700
Data Index: 21004 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.0752. Min Act: -0.1700
Data Index: 4172130 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.1065. Min Act: -0.1700
Data Index: 5929821 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.0440. Min Act: -0.1700
Data Index: 2315345 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.0752. Min Act: -0.1700
Data Index: 8104563 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.0440. Min Act: -0.1700
Data Index: 6102747 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.0440. Min Act: -0.1700
Data Index: 5263714 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.0440. Min Act: -0.1700
Data Index: 4349130 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.0127. Min Act: -0.1700
Data Index: 6820183 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2315. Min Range: -6.2315
Max Act: 5.9815. Min Act: -0.1700
Data Index: 3523125 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.0127. Min Act: -0.1700
Data Index: 5993335 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2315. Min Range: -6.2315
Max Act: 5.9815. Min Act: -0.1700
Data Index: 6961968 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2315. Min Range: -6.2315
Max Act: 5.9815. Min Act: -0.1700
Data Index: 8306051 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2315. Min Range: -6.2315
Max Act: 5.9815. Min Act: -0.1700
Data Index: 629445 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2315. Min Range: -6.2315
Max Act: 6.0127. Min Act: -0.1700
Data Index: 1970646 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2315. Min Range: -6.2315
Max Act: 5.9815. Min Act: -0.1700
Data Index: 5955071 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2315. Min Range: -6.2315
Max Act: 5.9502. Min Act: -0.1700
Data Index: 3513983 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2315. Min Range: -6.2315
Max Act: 5.9190. Min Act: -0.1700
Data Index: 5826516 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2315. Min Range: -6.2315
Max Act: 5.9502. Min Act: -0.1700
Data Index: 3519789 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19