Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3010 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0116. Min Range: -5.0116
Max Act: 5.0116. Min Act: -0.1700
Data Index: 7523477 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8553. Min Act: -0.1700
Data Index: 423474 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8553. Min Act: -0.1700
Data Index: 4582978 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8241. Min Act: -0.1700
Data Index: 5764933 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8241. Min Act: -0.1700
Data Index: 7601129 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8241. Min Act: -0.1700
Data Index: 347883 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7616. Min Act: -0.1700
Data Index: 5597141 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7928. Min Act: -0.1700
Data Index: 167748 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7303. Min Act: -0.1700
Data Index: 3721302 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7303. Min Act: -0.1700
Data Index: 7707163 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7616. Min Act: -0.1700
Data Index: 3997312 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7616. Min Act: -0.1700
Data Index: 8772166 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.6991. Min Act: -0.1700
Data Index: 4250830 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.6991. Min Act: -0.1700
Data Index: 4840025 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.6678. Min Act: -0.1700
Data Index: 5244380 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.6678. Min Act: -0.1700
Data Index: 2421386 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.6366. Min Act: -0.1700
Data Index: 4019453 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.6366. Min Act: -0.1700
Data Index: 4448624 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.6366. Min Act: -0.1700
Data Index: 8025422 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.6366. Min Act: -0.1700
Data Index: 8688132 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19