Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4436 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.9465. Min Act: -0.1700
Data Index: 6771680 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.8215. Min Act: -0.1700
Data Index: 5598019 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.8528. Min Act: -0.1700
Data Index: 1469734 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.7903. Min Act: -0.1700
Data Index: 115905 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.7278. Min Act: -0.1700
Data Index: 2813007 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.6653. Min Act: -0.1700
Data Index: 2813598 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.6653. Min Act: -0.1700
Data Index: 1736347 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.6340. Min Act: -0.1700
Data Index: 504897 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.6028. Min Act: -0.1700
Data Index: 6217075 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5715. Min Act: -0.1700
Data Index: 7097808 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5403. Min Act: -0.1700
Data Index: 255181 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5403. Min Act: -0.1700
Data Index: 8178715 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5403. Min Act: -0.1700
Data Index: 7359521 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5403. Min Act: -0.1700
Data Index: 4468329 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5403. Min Act: -0.1700
Data Index: 2507686 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5403. Min Act: -0.1700
Data Index: 5142331 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5090. Min Act: -0.1700
Data Index: 987729 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5090. Min Act: -0.1700
Data Index: 4972625 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.5090. Min Act: -0.1700
Data Index: 4251536 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9465. Min Range: -6.9465
Max Act: 6.4778. Min Act: -0.1700
Data Index: 6550559 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19