Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1389 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.8466. Min Act: -0.1700
Data Index: 5689234 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.6279. Min Act: -0.1700
Data Index: 1325230 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.5029. Min Act: -0.1700
Data Index: 7748960 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.3779. Min Act: -0.1700
Data Index: 7559592 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.3779. Min Act: -0.1700
Data Index: 6205242 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.3779. Min Act: -0.1700
Data Index: 5150668 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.3779. Min Act: -0.1700
Data Index: 8147766 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.3466. Min Act: -0.1700
Data Index: 5134813 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.3154. Min Act: -0.1700
Data Index: 1782017 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.3154. Min Act: -0.1700
Data Index: 801413 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2841. Min Act: -0.1700
Data Index: 8748897 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2841. Min Act: -0.1700
Data Index: 5134814 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2841. Min Act: -0.1700
Data Index: 1063379 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2841. Min Act: -0.1700
Data Index: 1942532 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2529. Min Act: -0.1700
Data Index: 4422722 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2529. Min Act: -0.1700
Data Index: 8660109 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2529. Min Act: -0.1700
Data Index: 2279478 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2529. Min Act: -0.1700
Data Index: 730761 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2529. Min Act: -0.1700
Data Index: 8564081 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8466. Min Range: -4.8466
Max Act: 4.2841. Min Act: -0.1700
Data Index: 7165022 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19