Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5476 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1077. Min Range: -6.1077
Max Act: 6.1077. Min Act: -0.1700
Data Index: 6314486 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.9202. Min Act: -0.1700
Data Index: 3544709 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.8890. Min Act: -0.1700
Data Index: 403182 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.8265. Min Act: -0.1700
Data Index: 4640745 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.8890. Min Act: -0.1700
Data Index: 7853045 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.7952. Min Act: -0.1700
Data Index: 5796184 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.7640. Min Act: -0.1700
Data Index: 5915315 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.7327. Min Act: -0.1700
Data Index: 5312722 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.7327. Min Act: -0.1700
Data Index: 2745790 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.7327. Min Act: -0.1700
Data Index: 6405276 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.7327. Min Act: -0.1700
Data Index: 3073533 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.6702. Min Act: -0.1700
Data Index: 4052722 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.7015. Min Act: -0.1700
Data Index: 3198704 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.7015. Min Act: -0.1700
Data Index: 6722135 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.6702. Min Act: -0.1700
Data Index: 7324565 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.6702. Min Act: -0.1700
Data Index: 4514446 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.6390. Min Act: -0.1700
Data Index: 6722136 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.6390. Min Act: -0.1700
Data Index: 994115 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.6390. Min Act: -0.1700
Data Index: 6348996 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1077. Min Range: -6.1077
Max Act: 5.6390. Min Act: -0.1700
Data Index: 11137 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19