Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.6899. Min Act: -0.1700
Data Index: 908948 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.6899. Min Act: -0.1700
Data Index: 7180421 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.6899. Min Act: -0.1700
Data Index: 8070441 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.6274. Min Act: -0.1700
Data Index: 8117206 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.6274. Min Act: -0.1700
Data Index: 3204396 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.4399. Min Act: -0.1700
Data Index: 8597427 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.5024. Min Act: -0.1700
Data Index: 7430496 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.4399. Min Act: -0.1700
Data Index: 2511056 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.3774. Min Act: -0.1700
Data Index: 42928 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.4399. Min Act: -0.1700
Data Index: 4229237 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.3774. Min Act: -0.1700
Data Index: 8599416 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.3149. Min Act: -0.1700
Data Index: 3792707 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.3149. Min Act: -0.1700
Data Index: 8795805 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.2524. Min Act: -0.1700
Data Index: 4891254 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.2524. Min Act: -0.1700
Data Index: 386824 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.1899. Min Act: -0.1700
Data Index: 1248455 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.1899. Min Act: -0.1700
Data Index: 6526649 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.1899. Min Act: -0.1700
Data Index: 4738183 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.1899. Min Act: -0.1700
Data Index: 8048587 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6899. Min Range: -9.6899
Max Act: 9.1899. Min Act: -0.1700
Data Index: 5198686 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19