Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1949. Min Range: -4.1949
Max Act: 4.1949. Min Act: -0.1700
Data Index: 7044194 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.9135. Min Act: -0.1700
Data Index: 7910266 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.8510. Min Act: -0.1700
Data Index: 434165 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.7884. Min Act: -0.1700
Data Index: 2635080 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.8197. Min Act: -0.1700
Data Index: 8164968 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.7884. Min Act: -0.1700
Data Index: 6663576 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.7572. Min Act: -0.1700
Data Index: 6663606 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.7259. Min Act: -0.1700
Data Index: 2635077 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.7572. Min Act: -0.1700
Data Index: 5928903 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.6946. Min Act: -0.1700
Data Index: 6663605 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.7259. Min Act: -0.1700
Data Index: 5880739 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.7572. Min Act: -0.1700
Data Index: 6630324 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.6946. Min Act: -0.1700
Data Index: 5830129 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.6946. Min Act: -0.1700
Data Index: 6766179 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.6946. Min Act: -0.1700
Data Index: 2129402 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.6790. Min Act: -0.1700
Data Index: 6630322 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.6790. Min Act: -0.1700
Data Index: 2457555 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.6946. Min Act: -0.1700
Data Index: 848661 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.6477. Min Act: -0.1700
Data Index: 6663586 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1949. Min Range: -4.1949
Max Act: 3.6320. Min Act: -0.1700
Data Index: 848655 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19