Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1912 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0004. Min Range: -8.0004
Max Act: 8.0004. Min Act: -0.1700
Data Index: 403844 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.9379. Min Act: -0.1700
Data Index: 32604 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.8129. Min Act: -0.1700
Data Index: 1573966 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.7504. Min Act: -0.1700
Data Index: 4599744 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.7504. Min Act: -0.1700
Data Index: 8821695 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.6254. Min Act: -0.1700
Data Index: 4591271 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.6254. Min Act: -0.1700
Data Index: 6635388 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.5629. Min Act: -0.1700
Data Index: 7699675 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.5629. Min Act: -0.1700
Data Index: 3148075 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.5317. Min Act: -0.1700
Data Index: 2121605 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.5004. Min Act: -0.1700
Data Index: 4833123 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.4067. Min Act: -0.1700
Data Index: 375453 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.4067. Min Act: -0.1700
Data Index: 3630923 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.3754. Min Act: -0.1700
Data Index: 2508434 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.3754. Min Act: -0.1700
Data Index: 8780195 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.4067. Min Act: -0.1700
Data Index: 2733296 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.3754. Min Act: -0.1700
Data Index: 7042887 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.3442. Min Act: -0.1700
Data Index: 5456168 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.3754. Min Act: -0.1700
Data Index: 7646662 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0004. Min Range: -8.0004
Max Act: 7.2817. Min Act: -0.1700
Data Index: 3453130 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19