Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2054. Min Range: -6.2054
Max Act: 6.2054. Min Act: -0.1700
Data Index: 8164337 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2054. Min Range: -6.2054
Max Act: 6.1429. Min Act: -0.1700
Data Index: 1886745 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2054. Min Range: -6.2054
Max Act: 6.0804. Min Act: -0.1700
Data Index: 5859043 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.9554. Min Act: -0.1700
Data Index: 5738501 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.8929. Min Act: -0.1700
Data Index: 4985077 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.8304. Min Act: -0.1700
Data Index: 4578991 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7992. Min Act: -0.1700
Data Index: 5952837 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.8304. Min Act: -0.1700
Data Index: 4093596 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7367. Min Act: -0.1700
Data Index: 8280796 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7679. Min Act: -0.1700
Data Index: 7964567 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7679. Min Act: -0.1700
Data Index: 4379561 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7679. Min Act: -0.1700
Data Index: 7558789 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7367. Min Act: -0.1700
Data Index: 8098415 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7367. Min Act: -0.1700
Data Index: 7444184 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7367. Min Act: -0.1700
Data Index: 8162807 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.6742. Min Act: -0.1700
Data Index: 7964563 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7054. Min Act: -0.1700
Data Index: 4075311 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7054. Min Act: -0.1700
Data Index: 5980930 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7054. Min Act: -0.1700
Data Index: 7964571 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2054. Min Range: -6.2054
Max Act: 5.7054. Min Act: -0.1700
Data Index: 5359084 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19