Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 76 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.9428. Min Act: -0.1700
Data Index: 7846263 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.9428. Min Act: -0.1700
Data Index: 6872983 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.9740. Min Act: -0.1700
Data Index: 6860704 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.9740. Min Act: -0.1700
Data Index: 2137188 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.8802. Min Act: -0.1700
Data Index: 3983900 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.8802. Min Act: -0.1700
Data Index: 5318129 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.8490. Min Act: -0.1700
Data Index: 5569226 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.8021. Min Act: -0.1700
Data Index: 5209300 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.8021. Min Act: -0.1700
Data Index: 6872592 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.7864. Min Act: -0.1700
Data Index: 8163142 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.7864. Min Act: -0.1700
Data Index: 8193009 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.7708. Min Act: -0.1700
Data Index: 2797466 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.7395. Min Act: -0.1700
Data Index: 4286518 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.7239. Min Act: -0.1700
Data Index: 2548908 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.7082. Min Act: -0.1700
Data Index: 2497377 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.6926. Min Act: -0.1700
Data Index: 8676938 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.6926. Min Act: -0.1700
Data Index: 442495 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.7239. Min Act: -0.1700
Data Index: 8687536 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.6926. Min Act: -0.1700
Data Index: 946934 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9740. Min Range: -3.9740
Max Act: 3.6926. Min Act: -0.1700
Data Index: 3640806 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19