Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3837 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.2402. Min Act: -0.1700
Data Index: 2664655 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.0527. Min Act: -0.1700
Data Index: 5996995 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2402. Min Range: -6.2402
Max Act: 6.0214. Min Act: -0.1700
Data Index: 5492244 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.9277. Min Act: -0.1700
Data Index: 1570362 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.9277. Min Act: -0.1700
Data Index: 7233880 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.9589. Min Act: -0.1700
Data Index: 5563028 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.9277. Min Act: -0.1700
Data Index: 4306906 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8964. Min Act: -0.1700
Data Index: 6124799 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8652. Min Act: -0.1700
Data Index: 2010993 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8652. Min Act: -0.1700
Data Index: 148008 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8339. Min Act: -0.1700
Data Index: 951081 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8339. Min Act: -0.1700
Data Index: 6415527 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8027. Min Act: -0.1700
Data Index: 7253145 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8339. Min Act: -0.1700
Data Index: 7793844 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.8027. Min Act: -0.1700
Data Index: 4852862 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.7714. Min Act: -0.1700
Data Index: 4393066 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.7402. Min Act: -0.1700
Data Index: 4427084 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.7714. Min Act: -0.1700
Data Index: 6860612 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.7714. Min Act: -0.1700
Data Index: 7938497 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2402. Min Range: -6.2402
Max Act: 5.7402. Min Act: -0.1700
Data Index: 1150676 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19