Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1343 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.9756. Min Act: -0.1699
Data Index: 6972232 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.9131. Min Act: -0.1700
Data Index: 6275855 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.8506. Min Act: -0.1700
Data Index: 3503234 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.7569. Min Act: -0.1700
Data Index: 7654042 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.7256. Min Act: -0.1700
Data Index: 7555463 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6944. Min Act: -0.1700
Data Index: 51016 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6944. Min Act: -0.1700
Data Index: 1347112 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6631. Min Act: -0.1700
Data Index: 2615415 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6631. Min Act: -0.1700
Data Index: 8827819 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6631. Min Act: -0.1700
Data Index: 2838924 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6631. Min Act: -0.1700
Data Index: 4036292 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6631. Min Act: -0.1700
Data Index: 4745439 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6319. Min Act: -0.1700
Data Index: 390555 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6006. Min Act: -0.1700
Data Index: 7648237 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6319. Min Act: -0.1700
Data Index: 2769374 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6319. Min Act: -0.1700
Data Index: 8166011 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.6006. Min Act: -0.1700
Data Index: 1059284 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.5381. Min Act: -0.1700
Data Index: 1133476 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.5381. Min Act: -0.1700
Data Index: 4297674 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9756. Min Range: -6.9756
Max Act: 6.5381. Min Act: -0.1700
Data Index: 7674540 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19