Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.5564. Min Act: -0.1700
Data Index: 1720427 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.3377. Min Act: -0.1700
Data Index: 4970945 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.2751. Min Act: -0.1700
Data Index: 1107766 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.2751. Min Act: -0.1700
Data Index: 942118 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.2439. Min Act: -0.1700
Data Index: 8810315 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.2126. Min Act: -0.1700
Data Index: 134086 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1814. Min Act: -0.1700
Data Index: 4429008 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1814. Min Act: -0.1700
Data Index: 8646100 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1814. Min Act: -0.1700
Data Index: 1785278 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1814. Min Act: -0.1700
Data Index: 3723680 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1501. Min Act: -0.1700
Data Index: 8726201 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1501. Min Act: -0.1700
Data Index: 6321272 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1189. Min Act: -0.1700
Data Index: 4773963 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1501. Min Act: -0.1700
Data Index: 4184941 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1189. Min Act: -0.1700
Data Index: 1424107 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1501. Min Act: -0.1700
Data Index: 8343143 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1189. Min Act: -0.1700
Data Index: 4631327 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.0876. Min Act: -0.1700
Data Index: 737915 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1189. Min Act: -0.1700
Data Index: 2009814 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5564. Min Range: -4.5564
Max Act: 4.1501. Min Act: -0.1700
Data Index: 8281398 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19