Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3711 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.8371. Min Act: -0.1700
Data Index: 3500090 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.2746. Min Act: -0.1700
Data Index: 2003623 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.2434. Min Act: -0.1700
Data Index: 2263513 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.2121. Min Act: -0.1700
Data Index: 553523 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.3059. Min Act: -0.1700
Data Index: 2697705 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.1809. Min Act: -0.1700
Data Index: 8691698 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.1184. Min Act: -0.1700
Data Index: 8188972 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.1496. Min Act: -0.1700
Data Index: 5047408 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.0559. Min Act: -0.1700
Data Index: 3623633 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.0871. Min Act: -0.1700
Data Index: 3931376 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.0559. Min Act: -0.1700
Data Index: 3193082 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.0559. Min Act: -0.1700
Data Index: 2301744 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 8484730 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 3975511 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 7998174 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.0871. Min Act: -0.1700
Data Index: 6515574 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8371. Min Range: -5.8371
Max Act: 4.9934. Min Act: -0.1700
Data Index: 2661151 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8371. Min Range: -5.8371
Max Act: 4.9934. Min Act: -0.1700
Data Index: 4789860 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8371. Min Range: -5.8371
Max Act: 5.0246. Min Act: -0.1700
Data Index: 3708870 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8371. Min Range: -5.8371
Max Act: 4.9934. Min Act: -0.1700
Data Index: 772076 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19