Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 770 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.2829. Min Act: -0.1700
Data Index: 6872595 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.2201. Min Act: -0.1700
Data Index: 3511630 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.2043. Min Act: -0.1700
Data Index: 6955018 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1886. Min Act: -0.1700
Data Index: 2267201 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1729. Min Act: -0.1700
Data Index: 6337770 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1414. Min Act: -0.1700
Data Index: 3558443 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1414. Min Act: -0.1700
Data Index: 6337765 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1572. Min Act: -0.1700
Data Index: 3625648 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1414. Min Act: -0.1700
Data Index: 6337762 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1572. Min Act: -0.1700
Data Index: 490248 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1414. Min Act: -0.1700
Data Index: 4060913 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1572. Min Act: -0.1700
Data Index: 6337780 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1257. Min Act: -0.1700
Data Index: 6337775 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1257. Min Act: -0.1700
Data Index: 2081122 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1414. Min Act: -0.1700
Data Index: 2605490 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1257. Min Act: -0.1700
Data Index: 6337768 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1257. Min Act: -0.1700
Data Index: 6337756 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1099. Min Act: -0.1700
Data Index: 4610252 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1257. Min Act: -0.1700
Data Index: 6337782 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2829. Min Range: -3.2829
Max Act: 3.1257. Min Act: -0.1700
Data Index: 6337754 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19