Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2244 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0571. Min Range: -10.0571
Max Act: 10.0571. Min Act: -0.1700
Data Index: 2739329 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.8696. Min Act: -0.1700
Data Index: 974842 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.8696. Min Act: -0.1700
Data Index: 8365298 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.8071. Min Act: -0.1700
Data Index: 4076342 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.6821. Min Act: -0.1700
Data Index: 3719155 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.7446. Min Act: -0.1700
Data Index: 6871 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.6821. Min Act: -0.1700
Data Index: 2326366 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.5571. Min Act: -0.1700
Data Index: 4472896 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.5571. Min Act: -0.1700
Data Index: 7231272 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.5571. Min Act: -0.1700
Data Index: 4934868 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.5571. Min Act: -0.1700
Data Index: 1565842 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.4946. Min Act: -0.1700
Data Index: 4327436 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.4321. Min Act: -0.1700
Data Index: 1503971 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.4321. Min Act: -0.1700
Data Index: 703344 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.3696. Min Act: -0.1700
Data Index: 1193529 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.3696. Min Act: -0.1700
Data Index: 4149174 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.3071. Min Act: -0.1700
Data Index: 3039149 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.3696. Min Act: -0.1700
Data Index: 1418239 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.3696. Min Act: -0.1700
Data Index: 1755683 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0571. Min Range: -10.0571
Max Act: 9.3071. Min Act: -0.1700
Data Index: 5401909 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19