Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4696 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.4311. Min Act: -0.1700
Data Index: 8819390 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3998. Min Act: -0.1700
Data Index: 3051676 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3998. Min Act: -0.1700
Data Index: 5446993 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3998. Min Act: -0.1700
Data Index: 3372163 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3998. Min Act: -0.1700
Data Index: 5259360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3998. Min Act: -0.1700
Data Index: 6364269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3998. Min Act: -0.1700
Data Index: 3692258 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3998. Min Act: -0.1700
Data Index: 7441141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3684. Min Act: -0.1700
Data Index: 6276629 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3684. Min Act: -0.1700
Data Index: 2482071 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3684. Min Act: -0.1700
Data Index: 8543719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3684. Min Act: -0.1700
Data Index: 2081028 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3684. Min Act: -0.1700
Data Index: 1897156 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3684. Min Act: -0.1700
Data Index: 7231947 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3684. Min Act: -0.1700
Data Index: 3472505 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3684. Min Act: -0.1700
Data Index: 1441704 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3684. Min Act: -0.1700
Data Index: 906058 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3371. Min Act: -0.1700
Data Index: 4842543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3057. Min Act: -0.1700
Data Index: 5504492 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4311. Min Range: -3.4311
Max Act: 3.3371. Min Act: -0.1700
Data Index: 3247682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19