Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.4373. Min Act: -0.1700
Data Index: 395041 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.2498. Min Act: -0.1700
Data Index: 5279629 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.1873. Min Act: -0.1700
Data Index: 7562824 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4373. Min Range: -5.4373
Max Act: 5.0623. Min Act: -0.1700
Data Index: 4531593 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.8435. Min Act: -0.1700
Data Index: 2479686 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.8435. Min Act: -0.1700
Data Index: 1998998 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.7498. Min Act: -0.1700
Data Index: 6054648 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.7810. Min Act: -0.1700
Data Index: 6201168 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.7498. Min Act: -0.1700
Data Index: 6201166 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.7185. Min Act: -0.1700
Data Index: 1584890 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.6873. Min Act: -0.1700
Data Index: 346381 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.6873. Min Act: -0.1700
Data Index: 4579194 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.6248. Min Act: -0.1700
Data Index: 1962782 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.5935. Min Act: -0.1700
Data Index: 8125546 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.5935. Min Act: -0.1700
Data Index: 2449182 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.5935. Min Act: -0.1700
Data Index: 5770903 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.5935. Min Act: -0.1700
Data Index: 5524434 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.5935. Min Act: -0.1700
Data Index: 7988885 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.5623. Min Act: -0.1700
Data Index: 2888334 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4373. Min Range: -5.4373
Max Act: 4.5935. Min Act: -0.1700
Data Index: 1590293 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19