Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5604 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.7638. Min Act: -0.1700
Data Index: 1633179 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.6075. Min Act: -0.1700
Data Index: 1684469 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5763. Min Act: -0.1700
Data Index: 5702419 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5450. Min Act: -0.1700
Data Index: 4145701 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5450. Min Act: -0.1700
Data Index: 335825 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5138. Min Act: -0.1700
Data Index: 3287469 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5450. Min Act: -0.1700
Data Index: 4968206 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5138. Min Act: -0.1700
Data Index: 4648509 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5138. Min Act: -0.1700
Data Index: 7817533 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5138. Min Act: -0.1700
Data Index: 1219365 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5138. Min Act: -0.1700
Data Index: 5280007 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.5138. Min Act: -0.1700
Data Index: 2373223 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.4825. Min Act: -0.1700
Data Index: 7107537 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.4513. Min Act: -0.1700
Data Index: 5429311 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.4513. Min Act: -0.1700
Data Index: 7694582 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.4513. Min Act: -0.1700
Data Index: 6844502 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.4513. Min Act: -0.1700
Data Index: 1480880 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.4513. Min Act: -0.1700
Data Index: 6927498 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.4513. Min Act: -0.1700
Data Index: 7705470 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7638. Min Range: -4.7638
Max Act: 4.4513. Min Act: -0.1700
Data Index: 2915963 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19