Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5466 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.9504. Min Act: -0.1700
Data Index: 1594250 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.8254. Min Act: -0.1700
Data Index: 15531 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.7316. Min Act: -0.1700
Data Index: 2002495 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.6691. Min Act: -0.1700
Data Index: 1350208 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.6066. Min Act: -0.1700
Data Index: 5117268 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.5129. Min Act: -0.1700
Data Index: 2242638 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4191. Min Act: -0.1700
Data Index: 3167940 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.4191. Min Act: -0.1700
Data Index: 2025567 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.3879. Min Act: -0.1700
Data Index: 7385769 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.3879. Min Act: -0.1700
Data Index: 1198818 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.3879. Min Act: -0.1700
Data Index: 2025568 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.3879. Min Act: -0.1700
Data Index: 3154692 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.3254. Min Act: -0.1700
Data Index: 4524551 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.3254. Min Act: -0.1700
Data Index: 1670735 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.2941. Min Act: -0.1700
Data Index: 7234164 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.2941. Min Act: -0.1700
Data Index: 6374309 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.2629. Min Act: -0.1700
Data Index: 1042563 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.2316. Min Act: -0.1700
Data Index: 5568724 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.2316. Min Act: -0.1700
Data Index: 2806269 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9504. Min Range: -6.9504
Max Act: 6.2004. Min Act: -0.1700
Data Index: 4199354 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19