Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3099 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 6914022 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.4503. Min Act: -0.1700
Data Index: 957860 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.4503. Min Act: -0.1700
Data Index: 1484037 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.4190. Min Act: -0.1700
Data Index: 361471 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.4190. Min Act: -0.1699
Data Index: 2519355 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.3878. Min Act: -0.1700
Data Index: 3501267 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.3878. Min Act: -0.1700
Data Index: 6892370 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.3878. Min Act: -0.1700
Data Index: 8773683 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.3878. Min Act: -0.1700
Data Index: 6317108 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.3565. Min Act: -0.1700
Data Index: 7206323 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.3253. Min Act: -0.1700
Data Index: 6704084 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.2940. Min Act: -0.1700
Data Index: 6429315 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.2628. Min Act: -0.1700
Data Index: 1163493 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.2628. Min Act: -0.1700
Data Index: 7972134 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.2315. Min Act: -0.1700
Data Index: 6654371 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.2003. Min Act: -0.1700
Data Index: 1952917 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.2315. Min Act: -0.1700
Data Index: 3057417 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.2315. Min Act: -0.1700
Data Index: 4777665 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.2315. Min Act: -0.1700
Data Index: 4898675 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5753. Min Range: -4.5753
Max Act: 4.2315. Min Act: -0.1700
Data Index: 3434641 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19