Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4893 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.3692. Min Act: -0.1700
Data Index: 3140671 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.2442. Min Act: -0.1700
Data Index: 5017132 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.1817. Min Act: -0.1700
Data Index: 891371 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.1504. Min Act: -0.1700
Data Index: 4896278 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.1504. Min Act: -0.1700
Data Index: 3327528 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0567. Min Act: -0.1700
Data Index: 8718946 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9942. Min Act: -0.1700
Data Index: 2144616 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9942. Min Act: -0.1700
Data Index: 4957128 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9629. Min Act: -0.1700
Data Index: 2056440 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9317. Min Act: -0.1700
Data Index: 909479 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9317. Min Act: -0.1700
Data Index: 8581635 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9317. Min Act: -0.1700
Data Index: 4159812 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9004. Min Act: -0.1700
Data Index: 5015647 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9004. Min Act: -0.1700
Data Index: 5341457 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8379. Min Act: -0.1700
Data Index: 3518690 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8692. Min Act: -0.1700
Data Index: 1792220 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.7754. Min Act: -0.1700
Data Index: 7842775 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8067. Min Act: -0.1700
Data Index: 6239101 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.7442. Min Act: -0.1700
Data Index: 1026660 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.7442. Min Act: -0.1700
Data Index: 6816799 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19