Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.9411. Min Act: -0.1700
Data Index: 3077940 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.5661. Min Act: -0.1700
Data Index: 3594893 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.5661. Min Act: -0.1700
Data Index: 54471 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.5036. Min Act: -0.1700
Data Index: 8058521 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.5661. Min Act: -0.1700
Data Index: 4789701 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.4724. Min Act: -0.1700
Data Index: 1263122 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.4724. Min Act: -0.1700
Data Index: 3055405 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.4724. Min Act: -0.1700
Data Index: 5227923 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.4411. Min Act: -0.1700
Data Index: 5385653 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.4411. Min Act: -0.1700
Data Index: 6729468 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.4411. Min Act: -0.1700
Data Index: 5111974 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.4411. Min Act: -0.1700
Data Index: 4194098 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.4099. Min Act: -0.1700
Data Index: 1197692 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.4099. Min Act: -0.1700
Data Index: 7640955 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.3786. Min Act: -0.1700
Data Index: 7017867 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.3786. Min Act: -0.1700
Data Index: 2487864 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.3786. Min Act: -0.1700
Data Index: 8286029 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.3474. Min Act: -0.1700
Data Index: 6133171 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.3474. Min Act: -0.1700
Data Index: 7917947 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9411. Min Range: -7.9411
Max Act: 7.3786. Min Act: -0.1700
Data Index: 8545275 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19