Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 457 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.6942. Min Act: -0.1700
Data Index: 3428548 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.3817. Min Act: -0.1700
Data Index: 10490 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.3192. Min Act: -0.1700
Data Index: 6447918 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.2879. Min Act: -0.1700
Data Index: 4994530 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.2879. Min Act: -0.1700
Data Index: 4249207 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.2254. Min Act: -0.1700
Data Index: 3046708 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.2254. Min Act: -0.1700
Data Index: 1612722 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.1942. Min Act: -0.1700
Data Index: 5276332 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.1004. Min Act: -0.1700
Data Index: 3581059 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.1004. Min Act: -0.1700
Data Index: 3057286 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.1317. Min Act: -0.1700
Data Index: 5647514 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.0692. Min Act: -0.1700
Data Index: 2499297 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.0692. Min Act: -0.1700
Data Index: 4465877 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.0067. Min Act: -0.1700
Data Index: 4391657 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.0692. Min Act: -0.1700
Data Index: 3710672 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.0067. Min Act: -0.1700
Data Index: 2299032 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6942. Min Range: -6.6942
Max Act: 6.0067. Min Act: -0.1700
Data Index: 6389615 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6942. Min Range: -6.6942
Max Act: 5.9754. Min Act: -0.1700
Data Index: 1270477 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6942. Min Range: -6.6942
Max Act: 5.9754. Min Act: -0.1700
Data Index: 70582 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6942. Min Range: -6.6942
Max Act: 5.9442. Min Act: -0.1700
Data Index: 2207341 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19