Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2450 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.8261. Min Act: -0.1700
Data Index: 8053537 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.7010. Min Act: -0.1700
Data Index: 8750522 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.6697. Min Act: -0.1700
Data Index: 363196 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.6384. Min Act: -0.1700
Data Index: 4670270 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.6228. Min Act: -0.1700
Data Index: 3503348 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.6384. Min Act: -0.1700
Data Index: 1223944 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.6071. Min Act: -0.1700
Data Index: 4077598 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5915. Min Act: -0.1700
Data Index: 5093912 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5758. Min Act: -0.1700
Data Index: 4868227 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5758. Min Act: -0.1700
Data Index: 3027842 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5758. Min Act: -0.1700
Data Index: 7432548 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5602. Min Act: -0.1700
Data Index: 577883 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5445. Min Act: -0.1700
Data Index: 8094167 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5445. Min Act: -0.1700
Data Index: 48370 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5289. Min Act: -0.1700
Data Index: 4343497 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5289. Min Act: -0.1700
Data Index: 2765213 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5132. Min Act: -0.1700
Data Index: 2219958 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5132. Min Act: -0.1700
Data Index: 8302693 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.4975. Min Act: -0.1700
Data Index: 6031045 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8261. Min Range: -3.8261
Max Act: 3.5132. Min Act: -0.1700
Data Index: 3027841 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19