Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2521 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0614. Min Range: -3.0614
Max Act: 3.0614. Min Act: -0.1700
Data Index: 1390977 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0614. Min Range: -3.0614
Max Act: 3.0456. Min Act: -0.1700
Data Index: 4442144 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0614. Min Range: -3.0614
Max Act: 3.0140. Min Act: -0.1700
Data Index: 4960266 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.9666. Min Act: -0.1700
Data Index: 895305 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.9349. Min Act: -0.1700
Data Index: 4902545 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.9033. Min Act: -0.1700
Data Index: 1975943 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8874. Min Act: -0.1700
Data Index: 5245298 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8715. Min Act: -0.1700
Data Index: 1044714 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8874. Min Act: -0.1700
Data Index: 3131240 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8874. Min Act: -0.1700
Data Index: 3294513 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8715. Min Act: -0.1700
Data Index: 7380705 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8874. Min Act: -0.1700
Data Index: 2999069 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8397. Min Act: -0.1700
Data Index: 6665111 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8556. Min Act: -0.1700
Data Index: 2538763 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8397. Min Act: -0.1700
Data Index: 5645943 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8238. Min Act: -0.1700
Data Index: 6869749 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8238. Min Act: -0.1700
Data Index: 1975106 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8397. Min Act: -0.1700
Data Index: 2060952 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8397. Min Act: -0.1700
Data Index: 5484648 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0614. Min Range: -3.0614
Max Act: 2.8238. Min Act: -0.1700
Data Index: 363967 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19