Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2869 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.2685. Min Act: -0.1700
Data Index: 5492076 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.2685. Min Act: -0.1700
Data Index: 3668237 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.1747. Min Act: -0.1700
Data Index: 38289 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.1747. Min Act: -0.1700
Data Index: 3608177 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.1435. Min Act: -0.1700
Data Index: 4602153 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.1122. Min Act: -0.1700
Data Index: 7706981 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.1435. Min Act: -0.1700
Data Index: 1032971 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.0810. Min Act: -0.1700
Data Index: 7749656 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.0810. Min Act: -0.1700
Data Index: 2354391 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.0810. Min Act: -0.1700
Data Index: 6291815 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.0497. Min Act: -0.1700
Data Index: 2418233 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.0184. Min Act: -0.1700
Data Index: 6591742 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.0184. Min Act: -0.1700
Data Index: 1513897 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.0184. Min Act: -0.1700
Data Index: 7453602 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2685. Min Range: -4.2685
Max Act: 4.0184. Min Act: -0.1700
Data Index: 375370 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2685. Min Range: -4.2685
Max Act: 3.9872. Min Act: -0.1700
Data Index: 6591727 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2685. Min Range: -4.2685
Max Act: 3.9559. Min Act: -0.1700
Data Index: 6591721 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2685. Min Range: -4.2685
Max Act: 3.9559. Min Act: -0.1700
Data Index: 3208679 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2685. Min Range: -4.2685
Max Act: 3.9559. Min Act: -0.1700
Data Index: 1026986 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2685. Min Range: -4.2685
Max Act: 3.9559. Min Act: -0.1700
Data Index: 2483876 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19