Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9038. Min Range: -7.9038
Max Act: 7.9038. Min Act: -0.1700
Data Index: 148660 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9038. Min Range: -7.9038
Max Act: 7.6538. Min Act: -0.1700
Data Index: 666833 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9038. Min Range: -7.9038
Max Act: 7.3413. Min Act: -0.1700
Data Index: 978105 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9038. Min Range: -7.9038
Max Act: 7.0913. Min Act: -0.1700
Data Index: 1630302 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9038. Min Range: -7.9038
Max Act: 7.0601. Min Act: -0.1700
Data Index: 3710348 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9038. Min Range: -7.9038
Max Act: 7.0601. Min Act: -0.1700
Data Index: 5145384 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9038. Min Range: -7.9038
Max Act: 7.0288. Min Act: -0.1700
Data Index: 2236140 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9038. Min Range: -7.9038
Max Act: 7.0288. Min Act: -0.1700
Data Index: 6405231 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.9663. Min Act: -0.1700
Data Index: 5888495 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.9351. Min Act: -0.1700
Data Index: 7753855 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.8726. Min Act: -0.1700
Data Index: 4133975 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.9038. Min Act: -0.1700
Data Index: 8193754 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.9038. Min Act: -0.1700
Data Index: 4086277 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.8726. Min Act: -0.1700
Data Index: 4344677 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.8101. Min Act: -0.1700
Data Index: 6413923 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.8413. Min Act: -0.1700
Data Index: 701501 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.8413. Min Act: -0.1700
Data Index: 3330579 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.8101. Min Act: -0.1700
Data Index: 194008 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.8101. Min Act: -0.1700
Data Index: 7500571 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9038. Min Range: -7.9038
Max Act: 6.8413. Min Act: -0.1700
Data Index: 5958893 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19