Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.8420. Min Act: -0.1700
Data Index: 8493505 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.6232. Min Act: -0.1700
Data Index: 397939 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.2482. Min Act: -0.1700
Data Index: 176496 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.1545. Min Act: -0.1700
Data Index: 2539573 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.1545. Min Act: -0.1700
Data Index: 5617405 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.1545. Min Act: -0.1700
Data Index: 8225247 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.1232. Min Act: -0.1700
Data Index: 4994439 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.0607. Min Act: -0.1700
Data Index: 6231824 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.1232. Min Act: -0.1700
Data Index: 6536589 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.0920. Min Act: -0.1700
Data Index: 560072 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.0607. Min Act: -0.1700
Data Index: 1955725 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.0295. Min Act: -0.1700
Data Index: 4028093 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8420. Min Range: -7.8420
Max Act: 7.0295. Min Act: -0.1700
Data Index: 7433743 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8420. Min Range: -7.8420
Max Act: 6.9982. Min Act: -0.1700
Data Index: 7447660 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8420. Min Range: -7.8420
Max Act: 6.9982. Min Act: -0.1699
Data Index: 8063435 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8420. Min Range: -7.8420
Max Act: 6.9982. Min Act: -0.1700
Data Index: 4048970 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8420. Min Range: -7.8420
Max Act: 6.9670. Min Act: -0.1700
Data Index: 8200068 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8420. Min Range: -7.8420
Max Act: 6.9670. Min Act: -0.1700
Data Index: 754084 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8420. Min Range: -7.8420
Max Act: 6.9670. Min Act: -0.1700
Data Index: 1300391 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8420. Min Range: -7.8420
Max Act: 6.9670. Min Act: -0.1700
Data Index: 6572843 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19