Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0669. Min Range: -7.0669
Max Act: 7.0669. Min Act: -0.1700
Data Index: 3974878 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.7232. Min Act: -0.1700
Data Index: 564685 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.4732. Min Act: -0.1700
Data Index: 6273776 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.3794. Min Act: -0.1700
Data Index: 8260761 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.3482. Min Act: -0.1700
Data Index: 4387667 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.4107. Min Act: -0.1700
Data Index: 5160279 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.3482. Min Act: -0.1700
Data Index: 4125818 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.3482. Min Act: -0.1700
Data Index: 393059 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.3482. Min Act: -0.1700
Data Index: 7144749 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.3169. Min Act: -0.1700
Data Index: 4388828 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.3169. Min Act: -0.1700
Data Index: 8068616 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.3169. Min Act: -0.1700
Data Index: 557422 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.2857. Min Act: -0.1700
Data Index: 8347091 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.2857. Min Act: -0.1700
Data Index: 6638134 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.2857. Min Act: -0.1700
Data Index: 3632485 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.3169. Min Act: -0.1700
Data Index: 4711842 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.2544. Min Act: -0.1700
Data Index: 8267532 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.2544. Min Act: -0.1700
Data Index: 2482964 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.2544. Min Act: -0.1700
Data Index: 1353134 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0669. Min Range: -7.0669
Max Act: 6.2544. Min Act: -0.1700
Data Index: 1732280 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19