Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 156 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1819. Min Range: -5.1819
Max Act: 5.1194. Min Act: -0.1700
Data Index: 4200040 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1819. Min Range: -5.1819
Max Act: 5.1819. Min Act: -0.1700
Data Index: 8686990 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1819. Min Range: -5.1819
Max Act: 5.1506. Min Act: -0.1700
Data Index: 3490744 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1819. Min Range: -5.1819
Max Act: 5.1194. Min Act: -0.1700
Data Index: 5143739 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1819. Min Range: -5.1819
Max Act: 5.1194. Min Act: -0.1700
Data Index: 7003635 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.9006. Min Act: -0.1700
Data Index: 3880853 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.9006. Min Act: -0.1700
Data Index: 5711797 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.9006. Min Act: -0.1700
Data Index: 4928551 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.9006. Min Act: -0.1700
Data Index: 2439149 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.8693. Min Act: -0.1700
Data Index: 901303 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.7756. Min Act: -0.1700
Data Index: 1769575 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.8068. Min Act: -0.1700
Data Index: 2424385 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.8381. Min Act: -0.1700
Data Index: 6074634 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.8068. Min Act: -0.1700
Data Index: 2242411 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.8381. Min Act: -0.1700
Data Index: 5650768 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.7443. Min Act: -0.1700
Data Index: 541764 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.8068. Min Act: -0.1700
Data Index: 6975544 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.7443. Min Act: -0.1700
Data Index: 7390896 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.7131. Min Act: -0.1700
Data Index: 2212488 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1819. Min Range: -5.1819
Max Act: 4.7131. Min Act: -0.1700
Data Index: 6490773 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19