Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2481 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.8954. Min Act: -0.1700
Data Index: 8734447 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.8954. Min Act: -0.1700
Data Index: 6419145 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.8329. Min Act: -0.1700
Data Index: 7387947 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.8329. Min Act: -0.1700
Data Index: 5979301 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.8016. Min Act: -0.1700
Data Index: 2596206 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.8016. Min Act: -0.1700
Data Index: 3292360 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.8016. Min Act: -0.1700
Data Index: 3816886 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.7704. Min Act: -0.1700
Data Index: 4410948 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.7704. Min Act: -0.1700
Data Index: 5294676 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.7704. Min Act: -0.1700
Data Index: 8659767 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.7391. Min Act: -0.1700
Data Index: 2071492 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.7391. Min Act: -0.1700
Data Index: 1110439 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.7391. Min Act: -0.1700
Data Index: 6410074 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.7079. Min Act: -0.1700
Data Index: 4649909 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.7079. Min Act: -0.1700
Data Index: 4462816 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.7079. Min Act: -0.1700
Data Index: 1981090 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.6766. Min Act: -0.1700
Data Index: 7435570 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.6766. Min Act: -0.1700
Data Index: 2855056 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.6766. Min Act: -0.1700
Data Index: 241606 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8954. Min Range: -5.8954
Max Act: 5.6766. Min Act: -0.1693
Data Index: 3594958 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19