Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.5395. Min Act: -0.1700
Data Index: 1218900 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.4770. Min Act: -0.1700
Data Index: 8373916 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.3520. Min Act: -0.1700
Data Index: 8373906 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.2895. Min Act: -0.1700
Data Index: 6196321 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.2895. Min Act: -0.1696
Data Index: 8626856 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.2270. Min Act: -0.1700
Data Index: 8373899 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.1957. Min Act: -0.1700
Data Index: 3170730 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.1645. Min Act: -0.1700
Data Index: 8373904 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.0707. Min Act: -0.1700
Data Index: 8373911 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5395. Min Range: -4.5395
Max Act: 4.0082. Min Act: -0.1700
Data Index: 1218906 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.9769. Min Act: -0.1700
Data Index: 3170731 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.9457. Min Act: -0.1700
Data Index: 8373905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.9144. Min Act: -0.1700
Data Index: 6196327 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.8831. Min Act: -0.1700
Data Index: 1218904 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.7893. Min Act: -0.1700
Data Index: 6196334 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.7893. Min Act: -0.1700
Data Index: 6196329 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.7580. Min Act: -0.1700
Data Index: 1218910 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.7268. Min Act: -0.1700
Data Index: 8626858 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.6955. Min Act: -0.1700
Data Index: 6196333 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5395. Min Range: -4.5395
Max Act: 3.6955. Min Act: -0.1700
Data Index: 6196331 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19