Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2052. Min Range: -3.2052
Max Act: 3.2052. Min Act: -0.1700
Data Index: 4158102 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2052. Min Range: -3.2052
Max Act: 3.2052. Min Act: -0.1700
Data Index: 439036 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2052. Min Range: -3.2052
Max Act: 3.0635. Min Act: -0.1700
Data Index: 6648733 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.9687. Min Act: -0.1700
Data Index: 546756 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.9370. Min Act: -0.1700
Data Index: 5703905 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.9370. Min Act: -0.1700
Data Index: 7997799 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.9212. Min Act: -0.1700
Data Index: 4681844 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.9212. Min Act: -0.1700
Data Index: 2359919 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.9212. Min Act: -0.1700
Data Index: 7046170 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.9053. Min Act: -0.1700
Data Index: 3148063 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8736. Min Act: -0.1700
Data Index: 534344 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8895. Min Act: -0.1700
Data Index: 6411881 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8895. Min Act: -0.1700
Data Index: 2959411 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8577. Min Act: -0.1700
Data Index: 6558609 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8577. Min Act: -0.1700
Data Index: 6319989 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8736. Min Act: -0.1700
Data Index: 557719 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8577. Min Act: -0.1700
Data Index: 7674191 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8577. Min Act: -0.1700
Data Index: 5311588 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8100. Min Act: -0.1700
Data Index: 1174944 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2052. Min Range: -3.2052
Max Act: 2.8418. Min Act: -0.1700
Data Index: 3555860 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19