Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4443 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.9640. Min Act: -0.1700
Data Index: 7695097 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.8702. Min Act: -0.1700
Data Index: 7882356 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.7765. Min Act: -0.1700
Data Index: 2482109 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.6827. Min Act: -0.1700
Data Index: 2078910 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.6827. Min Act: -0.1700
Data Index: 7893824 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.6515. Min Act: -0.1700
Data Index: 6158331 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.6202. Min Act: -0.1700
Data Index: 3962224 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.5265. Min Act: -0.1700
Data Index: 8340346 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.5265. Min Act: -0.1700
Data Index: 6764267 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4952. Min Act: -0.1700
Data Index: 610464 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.5265. Min Act: -0.1700
Data Index: 4413445 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4952. Min Act: -0.1700
Data Index: 2805253 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4640. Min Act: -0.1700
Data Index: 1321462 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4327. Min Act: -0.1700
Data Index: 4741582 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4327. Min Act: -0.1700
Data Index: 8111857 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4327. Min Act: -0.1700
Data Index: 3493075 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4327. Min Act: -0.1700
Data Index: 8572936 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4327. Min Act: -0.1700
Data Index: 5672037 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4327. Min Act: -0.1700
Data Index: 5275091 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9640. Min Range: -6.9640
Max Act: 6.4015. Min Act: -0.1700
Data Index: 4923244 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19