Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.3738. Min Act: -0.1700
Data Index: 8291745 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.3738. Min Act: -0.1700
Data Index: 3044598 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.3110. Min Act: -0.1700
Data Index: 5340912 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.2953. Min Act: -0.1700
Data Index: 5702545 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.2796. Min Act: -0.1700
Data Index: 2990323 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.2639. Min Act: -0.1700
Data Index: 1359128 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.2325. Min Act: -0.1700
Data Index: 824984 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.2325. Min Act: -0.1700
Data Index: 377346 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.2325. Min Act: -0.1700
Data Index: 6431555 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.2168. Min Act: -0.1700
Data Index: 3190418 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.2011. Min Act: -0.1700
Data Index: 5789872 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.2011. Min Act: -0.1700
Data Index: 5855579 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.1696. Min Act: -0.1700
Data Index: 5647998 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.1853. Min Act: -0.1700
Data Index: 2275868 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.1853. Min Act: -0.1700
Data Index: 6957778 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.1696. Min Act: -0.1700
Data Index: 4754451 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.1696. Min Act: -0.1700
Data Index: 4064159 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.1696. Min Act: -0.1700
Data Index: 4496111 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.1539. Min Act: -0.1700
Data Index: 1448147 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3738. Min Range: -3.3738
Max Act: 3.1539. Min Act: -0.1700
Data Index: 1917344 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19