Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1845 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0528. Min Range: -4.0528
Max Act: 4.0528. Min Act: -0.1700
Data Index: 2958582 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0528. Min Range: -4.0528
Max Act: 4.0215. Min Act: -0.1700
Data Index: 962005 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.9590. Min Act: -0.1700
Data Index: 6307257 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.9590. Min Act: -0.1700
Data Index: 1573728 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.9121. Min Act: -0.1700
Data Index: 49457 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.9121. Min Act: -0.1700
Data Index: 4118498 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.8965. Min Act: -0.1700
Data Index: 6823032 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.8809. Min Act: -0.1700
Data Index: 3618774 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.8652. Min Act: -0.1700
Data Index: 3640237 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.8496. Min Act: -0.1700
Data Index: 3347103 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.8183. Min Act: -0.1700
Data Index: 7966709 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.7870. Min Act: -0.1700
Data Index: 7083692 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.7870. Min Act: -0.1700
Data Index: 5490945 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.7714. Min Act: -0.1700
Data Index: 2380971 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.7714. Min Act: -0.1700
Data Index: 3262547 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.7558. Min Act: -0.1700
Data Index: 4915860 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.7714. Min Act: -0.1700
Data Index: 274175 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.7401. Min Act: -0.1700
Data Index: 6241470 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.7401. Min Act: -0.1700
Data Index: 6539961 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0528. Min Range: -4.0528
Max Act: 3.7401. Min Act: -0.1700
Data Index: 6658397 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19