Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1855. Min Range: -6.1855
Max Act: 6.1855. Min Act: -0.1700
Data Index: 7254704 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.8730. Min Act: -0.1700
Data Index: 2616021 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.8730. Min Act: -0.1700
Data Index: 6763513 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.8730. Min Act: -0.1700
Data Index: 4001109 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.6855. Min Act: -0.1700
Data Index: 1961527 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.6543. Min Act: -0.1700
Data Index: 1720130 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.6855. Min Act: -0.1700
Data Index: 6122091 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.6230. Min Act: -0.1700
Data Index: 790204 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.6543. Min Act: -0.1700
Data Index: 4877298 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.5918. Min Act: -0.1700
Data Index: 6765195 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.5918. Min Act: -0.1700
Data Index: 3392198 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.5605. Min Act: -0.1700
Data Index: 2122541 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.5293. Min Act: -0.1700
Data Index: 623705 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.5293. Min Act: -0.1700
Data Index: 5447428 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.4980. Min Act: -0.1700
Data Index: 8136848 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.4668. Min Act: -0.1700
Data Index: 1978729 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.4980. Min Act: -0.1700
Data Index: 8587904 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.5293. Min Act: -0.1700
Data Index: 8168983 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.4980. Min Act: -0.1700
Data Index: 2877829 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1855. Min Range: -6.1855
Max Act: 5.4668. Min Act: -0.1700
Data Index: 5297049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19