Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3843 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1971. Min Range: -3.1971
Max Act: 3.1971. Min Act: -0.1700
Data Index: 5073080 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1971. Min Range: -3.1971
Max Act: 3.1657. Min Act: -0.1700
Data Index: 1729851 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1971. Min Range: -3.1971
Max Act: 3.0554. Min Act: -0.1700
Data Index: 4882219 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1971. Min Range: -3.1971
Max Act: 3.0396. Min Act: -0.1700
Data Index: 6782832 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1971. Min Range: -3.1971
Max Act: 3.0080. Min Act: -0.1700
Data Index: 7421421 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1971. Min Range: -3.1971
Max Act: 3.0080. Min Act: -0.1700
Data Index: 3072458 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9606. Min Act: -0.1700
Data Index: 4055221 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9764. Min Act: -0.1700
Data Index: 6632271 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9447. Min Act: -0.1700
Data Index: 244847 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9447. Min Act: -0.1700
Data Index: 4417229 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9289. Min Act: -0.1700
Data Index: 5509552 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9289. Min Act: -0.1700
Data Index: 2021163 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9131. Min Act: -0.1700
Data Index: 3804928 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9131. Min Act: -0.1700
Data Index: 5850867 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.8972. Min Act: -0.1700
Data Index: 7345507 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.8972. Min Act: -0.1700
Data Index: 3627927 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9131. Min Act: -0.1700
Data Index: 7470242 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.8972. Min Act: -0.1700
Data Index: 8194060 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.9131. Min Act: -0.1700
Data Index: 5757662 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1971. Min Range: -3.1971
Max Act: 2.8813. Min Act: -0.1700
Data Index: 4208977 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19