Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1918 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0670. Min Range: -6.0670
Max Act: 6.0670. Min Act: -0.1700
Data Index: 5510930 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0670. Min Range: -6.0670
Max Act: 6.0045. Min Act: -0.1700
Data Index: 3303936 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.9420. Min Act: -0.1700
Data Index: 4120623 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.9733. Min Act: -0.1700
Data Index: 466404 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.9420. Min Act: -0.1700
Data Index: 4110106 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.9108. Min Act: -0.1700
Data Index: 6172316 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.9420. Min Act: -0.1700
Data Index: 4682167 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.9420. Min Act: -0.1700
Data Index: 275522 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.9108. Min Act: -0.1700
Data Index: 4170655 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8795. Min Act: -0.1700
Data Index: 6675830 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8795. Min Act: -0.1700
Data Index: 5290834 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8483. Min Act: -0.1700
Data Index: 741840 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.9108. Min Act: -0.1700
Data Index: 8325130 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8483. Min Act: -0.1700
Data Index: 1956840 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8795. Min Act: -0.1700
Data Index: 971348 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8795. Min Act: -0.1700
Data Index: 8100941 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8795. Min Act: -0.1700
Data Index: 7751588 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8170. Min Act: -0.1700
Data Index: 6720833 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8483. Min Act: -0.1700
Data Index: 3479065 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0670. Min Range: -6.0670
Max Act: 5.8483. Min Act: -0.1700
Data Index: 7065645 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19