Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.7935. Min Act: -0.1700
Data Index: 4657458 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.7623. Min Act: -0.1700
Data Index: 2540066 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.6060. Min Act: -0.1700
Data Index: 7174110 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.2935. Min Act: -0.1700
Data Index: 7387238 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.1998. Min Act: -0.1700
Data Index: 2862530 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.0748. Min Act: -0.1700
Data Index: 988197 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.0748. Min Act: -0.1700
Data Index: 3491535 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.0435. Min Act: -0.1700
Data Index: 7314016 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.0123. Min Act: -0.1700
Data Index: 3007125 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.0123. Min Act: -0.1700
Data Index: 7716563 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.0123. Min Act: -0.1700
Data Index: 4998032 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7935. Min Range: -5.7935
Max Act: 5.0123. Min Act: -0.1700
Data Index: 6616010 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7935. Min Range: -5.7935
Max Act: 4.9810. Min Act: -0.1700
Data Index: 7647050 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7935. Min Range: -5.7935
Max Act: 4.9810. Min Act: -0.1700
Data Index: 6778171 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7935. Min Range: -5.7935
Max Act: 4.9498. Min Act: -0.1700
Data Index: 7630017 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7935. Min Range: -5.7935
Max Act: 4.9498. Min Act: -0.1700
Data Index: 2689351 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7935. Min Range: -5.7935
Max Act: 4.9810. Min Act: -0.1700
Data Index: 8338775 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7935. Min Range: -5.7935
Max Act: 4.9498. Min Act: -0.1700
Data Index: 2522957 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7935. Min Range: -5.7935
Max Act: 4.9498. Min Act: -0.1700
Data Index: 16172 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7935. Min Range: -5.7935
Max Act: 4.9498. Min Act: -0.1700
Data Index: 7393702 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19