Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3325. Min Range: -7.3325
Max Act: 7.3325. Min Act: -0.1700
Data Index: 2846299 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3325. Min Range: -7.3325
Max Act: 7.1137. Min Act: -0.1700
Data Index: 3267156 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3325. Min Range: -7.3325
Max Act: 7.0825. Min Act: -0.1700
Data Index: 5480527 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3325. Min Range: -7.3325
Max Act: 7.0512. Min Act: -0.1700
Data Index: 1462934 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3325. Min Range: -7.3325
Max Act: 7.0825. Min Act: -0.1700
Data Index: 2820769 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3325. Min Range: -7.3325
Max Act: 7.0200. Min Act: -0.1700
Data Index: 5245746 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3325. Min Range: -7.3325
Max Act: 7.0200. Min Act: -0.1700
Data Index: 5982979 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3325. Min Range: -7.3325
Max Act: 7.0200. Min Act: -0.1700
Data Index: 6694499 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.9575. Min Act: -0.1700
Data Index: 8016445 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.9575. Min Act: -0.1700
Data Index: 7142095 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.9887. Min Act: -0.1700
Data Index: 156713 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.9887. Min Act: -0.1700
Data Index: 3684605 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.9575. Min Act: -0.1700
Data Index: 1501690 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.9575. Min Act: -0.1700
Data Index: 8364743 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.9575. Min Act: -0.1700
Data Index: 3943203 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.8950. Min Act: -0.1700
Data Index: 7246882 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.8950. Min Act: -0.1700
Data Index: 945884 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.8950. Min Act: -0.1700
Data Index: 1032750 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.8637. Min Act: -0.1700
Data Index: 66622 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3325. Min Range: -7.3325
Max Act: 6.8637. Min Act: -0.1700
Data Index: 6467065 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19