Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 365 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.4726. Min Act: -0.1700
Data Index: 3248655 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.3476. Min Act: -0.1700
Data Index: 6021721 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.2226. Min Act: -0.1700
Data Index: 7803511 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.1601. Min Act: -0.1700
Data Index: 3732714 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.1913. Min Act: -0.1700
Data Index: 8756551 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0976. Min Act: -0.1700
Data Index: 2120669 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0976. Min Act: -0.1700
Data Index: 2368253 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0976. Min Act: -0.1700
Data Index: 3963623 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0663. Min Act: -0.1700
Data Index: 4278810 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0663. Min Act: -0.1700
Data Index: 4718114 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0663. Min Act: -0.1700
Data Index: 5872023 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0351. Min Act: -0.1700
Data Index: 3424352 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0351. Min Act: -0.1700
Data Index: 6417760 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0351. Min Act: -0.1700
Data Index: 5186953 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0038. Min Act: -0.1700
Data Index: 7955890 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0351. Min Act: -0.1700
Data Index: 7177698 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4726. Min Range: -6.4726
Max Act: 6.0038. Min Act: -0.1700
Data Index: 6016755 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4726. Min Range: -6.4726
Max Act: 5.9726. Min Act: -0.1700
Data Index: 4426147 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4726. Min Range: -6.4726
Max Act: 5.9413. Min Act: -0.1700
Data Index: 1109314 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4726. Min Range: -6.4726
Max Act: 5.9726. Min Act: -0.1700
Data Index: 3871290 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19