Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5532. Min Range: -8.5532
Max Act: 8.5532. Min Act: -0.1700
Data Index: 5110317 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5532. Min Range: -8.5532
Max Act: 8.3657. Min Act: -0.1700
Data Index: 8027196 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5532. Min Range: -8.5532
Max Act: 8.3032. Min Act: -0.1700
Data Index: 7144137 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5532. Min Range: -8.5532
Max Act: 8.2407. Min Act: -0.1700
Data Index: 8406134 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5532. Min Range: -8.5532
Max Act: 8.2407. Min Act: -0.1700
Data Index: 4745165 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5532. Min Range: -8.5532
Max Act: 8.2407. Min Act: -0.1700
Data Index: 3643232 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5532. Min Range: -8.5532
Max Act: 8.0532. Min Act: -0.1700
Data Index: 6753080 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.9907. Min Act: -0.1700
Data Index: 5236735 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.9907. Min Act: -0.1700
Data Index: 5156784 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.9282. Min Act: -0.1700
Data Index: 3335874 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.9282. Min Act: -0.1700
Data Index: 3334368 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.9282. Min Act: -0.1700
Data Index: 3484821 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.9282. Min Act: -0.1700
Data Index: 8817529 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.8657. Min Act: -0.1700
Data Index: 6778869 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.8657. Min Act: -0.1700
Data Index: 6843574 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.8657. Min Act: -0.1700
Data Index: 3191403 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.8032. Min Act: -0.1700
Data Index: 8142937 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.8032. Min Act: -0.1700
Data Index: 3726624 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.8032. Min Act: -0.1700
Data Index: 2674333 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5532. Min Range: -8.5532
Max Act: 7.8032. Min Act: -0.1700
Data Index: 7183554 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19