Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4349 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.6316. Min Act: -0.1700
Data Index: 8158879 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5672. Min Act: -0.1700
Data Index: 3661825 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5511. Min Act: -0.1700
Data Index: 7110265 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5511. Min Act: -0.1700
Data Index: 6657445 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5188. Min Act: -0.1700
Data Index: 3894789 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5188. Min Act: -0.1700
Data Index: 4909089 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5188. Min Act: -0.1700
Data Index: 1529120 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5188. Min Act: -0.1700
Data Index: 5783386 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5188. Min Act: -0.1700
Data Index: 7379478 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4864. Min Act: -0.1700
Data Index: 6076736 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4864. Min Act: -0.1700
Data Index: 6279283 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5026. Min Act: -0.1700
Data Index: 4359100 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4864. Min Act: -0.1700
Data Index: 4308205 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.5026. Min Act: -0.1700
Data Index: 6316045 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4864. Min Act: -0.1700
Data Index: 6041364 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4539. Min Act: -0.1700
Data Index: 1631939 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4864. Min Act: -0.1700
Data Index: 2245596 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4539. Min Act: -0.1700
Data Index: 455965 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4701. Min Act: -0.1700
Data Index: 7196485 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6316. Min Range: -2.6316
Max Act: 2.4701. Min Act: -0.1700
Data Index: 1218001 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19