Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4890 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.2340. Min Act: -0.1700
Data Index: 7762321 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.2027. Min Act: -0.1700
Data Index: 2588845 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.2027. Min Act: -0.1700
Data Index: 667481 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.2027. Min Act: -0.1700
Data Index: 2588830 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.1402. Min Act: -0.1700
Data Index: 6035543 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.1715. Min Act: -0.1700
Data Index: 279932 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.1402. Min Act: -0.1700
Data Index: 2092151 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.1090. Min Act: -0.1700
Data Index: 6390123 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0777. Min Act: -0.1700
Data Index: 8500302 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0777. Min Act: -0.1700
Data Index: 5941438 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0777. Min Act: -0.1700
Data Index: 1242829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0777. Min Act: -0.1700
Data Index: 4633649 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0777. Min Act: -0.1700
Data Index: 3464100 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0465. Min Act: -0.1700
Data Index: 1088895 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0465. Min Act: -0.1700
Data Index: 1500254 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0465. Min Act: -0.1700
Data Index: 7982672 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0465. Min Act: -0.1700
Data Index: 5941431 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0465. Min Act: -0.1700
Data Index: 7338397 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0465. Min Act: -0.1700
Data Index: 6474291 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0465. Min Act: -0.1700
Data Index: 243067 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19