Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4094 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.9942. Min Act: -0.1700
Data Index: 8438961 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.9317. Min Act: -0.1700
Data Index: 1347647 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.8379. Min Act: -0.1700
Data Index: 7393096 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.9004. Min Act: -0.1700
Data Index: 2929785 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.9004. Min Act: -0.1700
Data Index: 8438963 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.8067. Min Act: -0.1700
Data Index: 5520432 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7754. Min Act: -0.1700
Data Index: 3692444 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7754. Min Act: -0.1700
Data Index: 2340376 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.8067. Min Act: -0.1700
Data Index: 5867191 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7754. Min Act: -0.1700
Data Index: 154005 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7754. Min Act: -0.1700
Data Index: 5598009 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.8067. Min Act: -0.1700
Data Index: 154003 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.8067. Min Act: -0.1700
Data Index: 6510566 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7754. Min Act: -0.1700
Data Index: 6785299 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7754. Min Act: -0.1700
Data Index: 8386444 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7754. Min Act: -0.1700
Data Index: 1614680 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7442. Min Act: -0.1700
Data Index: 3378813 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7129. Min Act: -0.1700
Data Index: 902227 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7442. Min Act: -0.1700
Data Index: 2586489 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9942. Min Range: -5.9942
Max Act: 5.7442. Min Act: -0.1700
Data Index: 8240147 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19