Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5525 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0375. Min Range: -5.0375
Max Act: 5.0375. Min Act: -0.1700
Data Index: 2170868 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.9125. Min Act: -0.1700
Data Index: 5046921 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.8500. Min Act: -0.1700
Data Index: 4853954 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.8500. Min Act: -0.1700
Data Index: 444289 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.8188. Min Act: -0.1700
Data Index: 5926594 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7875. Min Act: -0.1700
Data Index: 8563560 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7875. Min Act: -0.1700
Data Index: 6353248 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7875. Min Act: -0.1700
Data Index: 2462445 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7875. Min Act: -0.1700
Data Index: 1219559 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7563. Min Act: -0.1700
Data Index: 5811271 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7875. Min Act: -0.1700
Data Index: 5217707 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7563. Min Act: -0.1700
Data Index: 7490595 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7563. Min Act: -0.1700
Data Index: 3479553 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7563. Min Act: -0.1700
Data Index: 8642357 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7250. Min Act: -0.1700
Data Index: 1629915 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.6938. Min Act: -0.1700
Data Index: 3955238 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7250. Min Act: -0.1700
Data Index: 7398127 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7250. Min Act: -0.1700
Data Index: 494613 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.7250. Min Act: -0.1700
Data Index: 6406580 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0375. Min Range: -5.0375
Max Act: 4.6938. Min Act: -0.1700
Data Index: 2318411 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19