Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 224 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0671. Min Range: -7.0671
Max Act: 7.0671. Min Act: -0.1700
Data Index: 8476855 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0671. Min Range: -7.0671
Max Act: 7.0359. Min Act: -0.1700
Data Index: 8315756 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0671. Min Range: -7.0671
Max Act: 7.0046. Min Act: -0.1700
Data Index: 166323 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0671. Min Range: -7.0671
Max Act: 7.0359. Min Act: -0.1700
Data Index: 3249724 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.9421. Min Act: -0.1700
Data Index: 1914574 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.8796. Min Act: -0.1700
Data Index: 4292459 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.9109. Min Act: -0.1700
Data Index: 185765 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.8796. Min Act: -0.1700
Data Index: 7388621 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.8484. Min Act: -0.1700
Data Index: 5721647 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.8484. Min Act: -0.1700
Data Index: 6200900 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.8171. Min Act: -0.1700
Data Index: 5695783 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.7546. Min Act: -0.1700
Data Index: 511653 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.7234. Min Act: -0.1700
Data Index: 4169975 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.7546. Min Act: -0.1700
Data Index: 1452438 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.7234. Min Act: -0.1700
Data Index: 6262580 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.7234. Min Act: -0.1700
Data Index: 7639531 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.7234. Min Act: -0.1700
Data Index: 5335150 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.6921. Min Act: -0.1700
Data Index: 1200582 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.6609. Min Act: -0.1700
Data Index: 1746152 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0671. Min Range: -7.0671
Max Act: 6.6296. Min Act: -0.1700
Data Index: 5720106 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19