Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 564 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0142. Min Range: -3.0142
Max Act: 3.0142. Min Act: -0.1700
Data Index: 7487503 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.9984. Min Act: -0.1700
Data Index: 6403641 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.9826. Min Act: -0.1700
Data Index: 6898691 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.9984. Min Act: -0.1700
Data Index: 1931782 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.9509. Min Act: -0.1700
Data Index: 4425298 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.9509. Min Act: -0.1700
Data Index: 5102523 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.9509. Min Act: -0.1700
Data Index: 5474465 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.9351. Min Act: -0.1700
Data Index: 8314949 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.9034. Min Act: -0.1700
Data Index: 3253486 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8876. Min Act: -0.1700
Data Index: 5949068 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8717. Min Act: -0.1700
Data Index: 8729644 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8717. Min Act: -0.1700
Data Index: 7962700 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8558. Min Act: -0.1700
Data Index: 6555944 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8558. Min Act: -0.1700
Data Index: 1143049 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8240. Min Act: -0.1700
Data Index: 7659084 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8240. Min Act: -0.1700
Data Index: 2198985 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8240. Min Act: -0.1700
Data Index: 6270297 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8240. Min Act: -0.1700
Data Index: 5670536 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8399. Min Act: -0.1700
Data Index: 5600005 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0142. Min Range: -3.0142
Max Act: 2.8240. Min Act: -0.1700
Data Index: 2506733 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19