Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.8657. Min Act: -0.1700
Data Index: 3520164 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.8345. Min Act: -0.1700
Data Index: 2436663 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.7407. Min Act: -0.1700
Data Index: 2436918 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.7407. Min Act: -0.1700
Data Index: 2510749 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.5220. Min Act: -0.1700
Data Index: 1433467 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.5220. Min Act: -0.1700
Data Index: 6044852 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.4907. Min Act: -0.1700
Data Index: 4315567 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.4907. Min Act: -0.1700
Data Index: 7972380 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.5220. Min Act: -0.1700
Data Index: 8362077 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.4595. Min Act: -0.1700
Data Index: 8550137 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.4282. Min Act: -0.1700
Data Index: 3457496 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.4282. Min Act: -0.1700
Data Index: 3712822 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.4282. Min Act: -0.1700
Data Index: 7221568 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.4282. Min Act: -0.1700
Data Index: 6966286 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.3970. Min Act: -0.1700
Data Index: 4315952 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.4282. Min Act: -0.1700
Data Index: 930419 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.3970. Min Act: -0.1700
Data Index: 652404 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.3657. Min Act: -0.1700
Data Index: 8176700 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.3657. Min Act: -0.1700
Data Index: 4098033 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8657. Min Range: -5.8657
Max Act: 5.3657. Min Act: -0.1700
Data Index: 5578504 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19