Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.4600. Min Act: -0.1700
Data Index: 2832153 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.4600. Min Act: -0.1700
Data Index: 6949599 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.4274. Min Act: -0.1700
Data Index: 4917008 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.4111. Min Act: -0.1700
Data Index: 1132225 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.4111. Min Act: -0.1700
Data Index: 4773591 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3948. Min Act: -0.1700
Data Index: 606381 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3948. Min Act: -0.1700
Data Index: 6632759 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3785. Min Act: -0.1700
Data Index: 8811423 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3948. Min Act: -0.1700
Data Index: 6488579 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3785. Min Act: -0.1700
Data Index: 5977366 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3785. Min Act: -0.1700
Data Index: 3421898 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3785. Min Act: -0.1700
Data Index: 3299782 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3785. Min Act: -0.1700
Data Index: 906600 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3785. Min Act: -0.1700
Data Index: 4531417 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3621. Min Act: -0.1700
Data Index: 4743771 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3458. Min Act: -0.1700
Data Index: 7337120 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3621. Min Act: -0.1700
Data Index: 5060350 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3621. Min Act: -0.1700
Data Index: 4513982 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3621. Min Act: -0.1700
Data Index: 5811352 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4600. Min Range: -2.4600
Max Act: 2.3458. Min Act: -0.1700
Data Index: 318065 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19