Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.4380. Min Act: -0.1700
Data Index: 4631885 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.4692. Min Act: -0.1700
Data Index: 3391573 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.4067. Min Act: -0.1700
Data Index: 4222312 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.4067. Min Act: -0.1700
Data Index: 7272352 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.3130. Min Act: -0.1700
Data Index: 4345831 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.2505. Min Act: -0.1700
Data Index: 5395899 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.2192. Min Act: -0.1700
Data Index: 1825971 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.2505. Min Act: -0.1700
Data Index: 3819286 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.2505. Min Act: -0.1700
Data Index: 1007363 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.2505. Min Act: -0.1700
Data Index: 1349556 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.1880. Min Act: -0.1700
Data Index: 387366 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.2192. Min Act: -0.1700
Data Index: 5299486 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.2192. Min Act: -0.1700
Data Index: 121051 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.1880. Min Act: -0.1700
Data Index: 7955755 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.2192. Min Act: -0.1700
Data Index: 2957359 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.1880. Min Act: -0.1700
Data Index: 8033319 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.1880. Min Act: -0.1700
Data Index: 3897925 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.1567. Min Act: -0.1700
Data Index: 5959751 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.1255. Min Act: -0.1700
Data Index: 3831812 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4692. Min Range: -6.4692
Max Act: 6.1255. Min Act: -0.1700
Data Index: 3409670 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19