Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.8148. Min Act: -0.1700
Data Index: 6029048 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7671. Min Act: -0.1700
Data Index: 2451079 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7511. Min Act: -0.1700
Data Index: 2245722 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7351. Min Act: -0.1700
Data Index: 525214 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7511. Min Act: -0.1700
Data Index: 1344791 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7032. Min Act: -0.1700
Data Index: 1818170 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7032. Min Act: -0.1700
Data Index: 8407986 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7191. Min Act: -0.1700
Data Index: 8348523 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7032. Min Act: -0.1700
Data Index: 6069385 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7032. Min Act: -0.1700
Data Index: 8189952 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7032. Min Act: -0.1700
Data Index: 4781175 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7032. Min Act: -0.1700
Data Index: 1301527 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7032. Min Act: -0.1700
Data Index: 1806866 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.6871. Min Act: -0.1700
Data Index: 2428104 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.7191. Min Act: -0.1700
Data Index: 1906241 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.6871. Min Act: -0.1700
Data Index: 6547456 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.6551. Min Act: -0.1700
Data Index: 3221554 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.6551. Min Act: -0.1700
Data Index: 4885613 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.6230. Min Act: -0.1700
Data Index: 7709197 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8148. Min Range: -2.8148
Max Act: 2.6551. Min Act: -0.1700
Data Index: 1605227 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19