Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5854. Min Act: -0.1700
Data Index: 2729424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5854. Min Act: -0.1700
Data Index: 7648981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5227. Min Act: -0.1700
Data Index: 7868726 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5854. Min Act: -0.1700
Data Index: 4921527 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5227. Min Act: -0.1700
Data Index: 5684893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4914. Min Act: -0.1700
Data Index: 1358041 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5227. Min Act: -0.1700
Data Index: 7961284 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5227. Min Act: -0.1700
Data Index: 2589051 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5227. Min Act: -0.1700
Data Index: 7777334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5227. Min Act: -0.1700
Data Index: 6041391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.5227. Min Act: -0.1700
Data Index: 5913677 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4914. Min Act: -0.1700
Data Index: 2293177 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4601. Min Act: -0.1700
Data Index: 4441424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4601. Min Act: -0.1700
Data Index: 715110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4914. Min Act: -0.1700
Data Index: 7512821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4914. Min Act: -0.1700
Data Index: 7466124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4914. Min Act: -0.1700
Data Index: 8205058 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4914. Min Act: -0.1698
Data Index: 7218104 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4914. Min Act: -0.1700
Data Index: 3414036 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5854. Min Range: -3.5854
Max Act: 3.4601. Min Act: -0.1700
Data Index: 7173347 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19