Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 626 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1628. Min Range: -9.1628
Max Act: 9.1628. Min Act: -0.1700
Data Index: 479823 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.7878. Min Act: -0.1700
Data Index: 8480861 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.7253. Min Act: -0.1700
Data Index: 8188422 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.6628. Min Act: -0.1700
Data Index: 1584660 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.5378. Min Act: -0.1700
Data Index: 7503442 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.6003. Min Act: -0.1700
Data Index: 3338385 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.6003. Min Act: -0.1700
Data Index: 5676997 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.5378. Min Act: -0.1700
Data Index: 2628666 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.5378. Min Act: -0.1700
Data Index: 65159 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.4753. Min Act: -0.1700
Data Index: 937559 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.4128. Min Act: -0.1700
Data Index: 7053657 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.4128. Min Act: -0.1700
Data Index: 208333 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.3503. Min Act: -0.1700
Data Index: 1995231 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.2878. Min Act: -0.1700
Data Index: 4848667 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.3503. Min Act: -0.1700
Data Index: 5403486 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.3503. Min Act: -0.1700
Data Index: 4683744 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.3503. Min Act: -0.1700
Data Index: 4117259 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.3503. Min Act: -0.1700
Data Index: 6709588 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.4128. Min Act: -0.1700
Data Index: 1926412 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1628. Min Range: -9.1628
Max Act: 8.3503. Min Act: -0.1700
Data Index: 6618276 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19