Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1233 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2278. Min Range: -7.2278
Max Act: 7.2278. Min Act: -0.1700
Data Index: 2891649 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2278. Min Range: -7.2278
Max Act: 7.1653. Min Act: -0.1700
Data Index: 1252899 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2278. Min Range: -7.2278
Max Act: 7.0403. Min Act: -0.1700
Data Index: 2934143 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2278. Min Range: -7.2278
Max Act: 7.0403. Min Act: -0.1700
Data Index: 6415012 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2278. Min Range: -7.2278
Max Act: 7.0090. Min Act: -0.1700
Data Index: 1577760 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.9153. Min Act: -0.1700
Data Index: 4573272 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.8528. Min Act: -0.1700
Data Index: 4800192 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.8528. Min Act: -0.1700
Data Index: 4573278 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.8840. Min Act: -0.1700
Data Index: 5367631 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.7590. Min Act: -0.1700
Data Index: 995621 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.7278. Min Act: -0.1700
Data Index: 4426977 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.6965. Min Act: -0.1700
Data Index: 8093503 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.6965. Min Act: -0.1700
Data Index: 1801953 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.6028. Min Act: -0.1700
Data Index: 6314729 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5403. Min Act: -0.1700
Data Index: 6660662 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5403. Min Act: -0.1700
Data Index: 5819499 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5090. Min Act: -0.1700
Data Index: 555152 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.4778. Min Act: -0.1700
Data Index: 2383333 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5090. Min Act: -0.1700
Data Index: 5745690 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.4465. Min Act: -0.1700
Data Index: 2451810 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19