Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5525 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.7404. Min Act: -0.1700
Data Index: 7693018 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.4279. Min Act: -0.1700
Data Index: 395380 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.3654. Min Act: -0.1700
Data Index: 7738117 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.2404. Min Act: -0.1700
Data Index: 2808543 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.1779. Min Act: -0.1700
Data Index: 6383982 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.1779. Min Act: -0.1700
Data Index: 4782348 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.1466. Min Act: -0.1700
Data Index: 3047894 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.0841. Min Act: -0.1700
Data Index: 734542 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.0841. Min Act: -0.1700
Data Index: 4921274 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.0841. Min Act: -0.1700
Data Index: 6695682 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.0529. Min Act: -0.1700
Data Index: 4405759 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.0529. Min Act: -0.1700
Data Index: 7723550 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.0216. Min Act: -0.1700
Data Index: 4602312 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.0529. Min Act: -0.1700
Data Index: 6371180 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7404. Min Range: -6.7404
Max Act: 6.0216. Min Act: -0.1700
Data Index: 3976385 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7404. Min Range: -6.7404
Max Act: 5.9591. Min Act: -0.1700
Data Index: 160930 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7404. Min Range: -6.7404
Max Act: 5.9904. Min Act: -0.1700
Data Index: 3603464 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7404. Min Range: -6.7404
Max Act: 5.9591. Min Act: -0.1700
Data Index: 2278654 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7404. Min Range: -6.7404
Max Act: 5.9591. Min Act: -0.1700
Data Index: 6396279 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7404. Min Range: -6.7404
Max Act: 5.9591. Min Act: -0.1700
Data Index: 1500383 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19