Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.5671. Min Act: -0.1700
Data Index: 4310148 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.5046. Min Act: -0.1700
Data Index: 646792 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.4108. Min Act: -0.1700
Data Index: 4275997 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.4108. Min Act: -0.1700
Data Index: 3213395 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.3796. Min Act: -0.1700
Data Index: 5047416 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.3796. Min Act: -0.1700
Data Index: 3807739 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.3483. Min Act: -0.1700
Data Index: 96460 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.3483. Min Act: -0.1700
Data Index: 4188418 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.3171. Min Act: -0.1700
Data Index: 2242809 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.3171. Min Act: -0.1700
Data Index: 1596039 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.3171. Min Act: -0.1700
Data Index: 1804416 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.3171. Min Act: -0.1700
Data Index: 5047415 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.2546. Min Act: -0.1700
Data Index: 4016200 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.2546. Min Act: -0.1700
Data Index: 6170446 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.2546. Min Act: -0.1700
Data Index: 7574339 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.2546. Min Act: -0.1700
Data Index: 8477187 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.2546. Min Act: -0.1700
Data Index: 7574342 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.2233. Min Act: -0.1700
Data Index: 5485046 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.1921. Min Act: -0.1700
Data Index: 2746348 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5671. Min Range: -4.5671
Max Act: 4.1608. Min Act: -0.1700
Data Index: 3909134 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19