Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1773 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.2610. Min Act: -0.1700
Data Index: 2536795 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1985. Min Act: -0.1700
Data Index: 5172236 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1360. Min Act: -0.1700
Data Index: 3040943 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 444175 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 3982483 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 2053216 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 3621194 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 4296487 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 1821300 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 6300081 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 5676038 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 2509546 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 3467566 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0110. Min Act: -0.1700
Data Index: 5279544 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 7549785 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 1669807 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 6402071 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 1188608 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 6658419 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 2992906 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19