Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.5555. Min Act: -0.1700
Data Index: 2922805 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.4305. Min Act: -0.1700
Data Index: 1673518 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.4617. Min Act: -0.1700
Data Index: 4711093 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3992. Min Act: -0.1700
Data Index: 8447034 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.4305. Min Act: -0.1700
Data Index: 335112 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3992. Min Act: -0.1700
Data Index: 1891480 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3992. Min Act: -0.1700
Data Index: 3414493 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3680. Min Act: -0.1700
Data Index: 7875617 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3680. Min Act: -0.1700
Data Index: 7193163 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3680. Min Act: -0.1700
Data Index: 8702583 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3992. Min Act: -0.1700
Data Index: 7502270 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3367. Min Act: -0.1700
Data Index: 8473814 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3055. Min Act: -0.1700
Data Index: 787559 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3055. Min Act: -0.1700
Data Index: 31621 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3367. Min Act: -0.1700
Data Index: 8686639 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3055. Min Act: -0.1700
Data Index: 2947003 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.2742. Min Act: -0.1700
Data Index: 6937745 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3055. Min Act: -0.1700
Data Index: 7810940 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.3055. Min Act: -0.1700
Data Index: 8710542 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5555. Min Range: -4.5555
Max Act: 4.2742. Min Act: -0.1700
Data Index: 7520680 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19