Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4567. Min Range: -8.4567
Max Act: 8.4567. Min Act: -0.1700
Data Index: 4648184 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4567. Min Range: -8.4567
Max Act: 8.2692. Min Act: -0.1700
Data Index: 3239375 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4567. Min Range: -8.4567
Max Act: 8.2692. Min Act: -0.1700
Data Index: 2223344 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4567. Min Range: -8.4567
Max Act: 8.1442. Min Act: -0.1700
Data Index: 7370778 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4567. Min Range: -8.4567
Max Act: 8.0817. Min Act: -0.1700
Data Index: 6904709 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4567. Min Range: -8.4567
Max Act: 8.0817. Min Act: -0.1700
Data Index: 3359773 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4567. Min Range: -8.4567
Max Act: 8.0192. Min Act: -0.1700
Data Index: 8192560 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4567. Min Range: -8.4567
Max Act: 8.0192. Min Act: -0.1700
Data Index: 851464 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.9567. Min Act: -0.1700
Data Index: 7962611 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4567. Min Range: -8.4567
Max Act: 8.0192. Min Act: -0.1700
Data Index: 2605837 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.9567. Min Act: -0.1700
Data Index: 297830 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.9567. Min Act: -0.1700
Data Index: 7017289 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.9254. Min Act: -0.1700
Data Index: 4840718 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.9567. Min Act: -0.1700
Data Index: 5808269 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.8942. Min Act: -0.1700
Data Index: 6774695 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.8317. Min Act: -0.1700
Data Index: 5720250 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.8317. Min Act: -0.1700
Data Index: 5789328 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.7692. Min Act: -0.1700
Data Index: 2647533 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.8004. Min Act: -0.1700
Data Index: 5360283 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4567. Min Range: -8.4567
Max Act: 7.7379. Min Act: -0.1700
Data Index: 6688096 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19