Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6018 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1340. Min Range: -5.1340
Max Act: 5.1340. Min Act: -0.1700
Data Index: 1113084 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1340. Min Range: -5.1340
Max Act: 5.1340. Min Act: -0.1700
Data Index: 1747948 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1340. Min Range: -5.1340
Max Act: 5.1028. Min Act: -0.1700
Data Index: 4576266 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.9465. Min Act: -0.1700
Data Index: 4331006 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.8528. Min Act: -0.1700
Data Index: 5472744 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.8840. Min Act: -0.1700
Data Index: 7531521 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.8840. Min Act: -0.1700
Data Index: 8026573 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.8528. Min Act: -0.1700
Data Index: 2637043 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.8215. Min Act: -0.1700
Data Index: 1028144 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.8215. Min Act: -0.1700
Data Index: 8000612 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7903. Min Act: -0.1700
Data Index: 3190067 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7903. Min Act: -0.1700
Data Index: 7006101 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7903. Min Act: -0.1700
Data Index: 3704658 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7278. Min Act: -0.1700
Data Index: 3992272 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7903. Min Act: -0.1700
Data Index: 7905356 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7590. Min Act: -0.1700
Data Index: 1444798 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7590. Min Act: -0.1700
Data Index: 7003882 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7278. Min Act: -0.1700
Data Index: 211625 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7278. Min Act: -0.1700
Data Index: 4576634 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1340. Min Range: -5.1340
Max Act: 4.7278. Min Act: -0.1700
Data Index: 5248698 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19