Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0568. Min Range: -5.0568
Max Act: 5.0568. Min Act: -0.1700
Data Index: 3675937 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.9943. Min Act: -0.1700
Data Index: 8296770 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.9631. Min Act: -0.1700
Data Index: 6917132 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.9631. Min Act: -0.1700
Data Index: 2842819 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.9631. Min Act: -0.1700
Data Index: 848588 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.9631. Min Act: -0.1700
Data Index: 4960166 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.8693. Min Act: -0.1700
Data Index: 2280981 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.8693. Min Act: -0.1700
Data Index: 3628416 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.8381. Min Act: -0.1700
Data Index: 3102347 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.8693. Min Act: -0.1700
Data Index: 7522501 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.8693. Min Act: -0.1700
Data Index: 403987 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.8381. Min Act: -0.1700
Data Index: 2796357 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.8381. Min Act: -0.1700
Data Index: 8004478 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.7443. Min Act: -0.1700
Data Index: 2484096 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.7756. Min Act: -0.1700
Data Index: 246650 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.7756. Min Act: -0.1700
Data Index: 3660207 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.7443. Min Act: -0.1700
Data Index: 135935 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.7756. Min Act: -0.1700
Data Index: 6871566 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.7443. Min Act: -0.1700
Data Index: 3906658 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0568. Min Range: -5.0568
Max Act: 4.7443. Min Act: -0.1700
Data Index: 518704 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19