Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 790 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.8064. Min Act: -0.1700
Data Index: 4938390 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.7586. Min Act: -0.1700
Data Index: 245552 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.6787. Min Act: -0.1700
Data Index: 6715025 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.6466. Min Act: -0.1700
Data Index: 7246693 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.5984. Min Act: -0.1700
Data Index: 2841763 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.5662. Min Act: -0.1700
Data Index: 1678711 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.5500. Min Act: -0.1700
Data Index: 8221658 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.5500. Min Act: -0.1700
Data Index: 4011430 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.5015. Min Act: -0.1700
Data Index: 91913 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4853. Min Act: -0.1700
Data Index: 7305704 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4853. Min Act: -0.1700
Data Index: 2718020 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.5015. Min Act: -0.1700
Data Index: 874927 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4691. Min Act: -0.1700
Data Index: 5370235 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4691. Min Act: -0.1700
Data Index: 1163659 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4691. Min Act: -0.1700
Data Index: 1726797 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4691. Min Act: -0.1700
Data Index: 1579810 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4691. Min Act: -0.1700
Data Index: 2004163 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4528. Min Act: -0.1700
Data Index: 8658855 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4366. Min Act: -0.1700
Data Index: 8438318 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8064. Min Range: -2.8064
Max Act: 2.4528. Min Act: -0.1700
Data Index: 7169560 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19