Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2657. Min Act: -0.1697
Data Index: 5555616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2345. Min Act: -0.1700
Data Index: 6278411 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2032. Min Act: -0.1700
Data Index: 1342721 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2345. Min Act: -0.1696
Data Index: 2586986 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2032. Min Act: -0.1699
Data Index: 1362016 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1720. Min Act: -0.1700
Data Index: 2393962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1720. Min Act: -0.1695
Data Index: 6651822 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1720. Min Act: -0.1698
Data Index: 4234666 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1407. Min Act: -0.1700
Data Index: 2102863 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1407. Min Act: -0.1700
Data Index: 4804719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1407. Min Act: -0.1700
Data Index: 1425656 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.0782. Min Act: -0.1700
Data Index: 3113460 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1095. Min Act: -0.1700
Data Index: 861493 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1095. Min Act: -0.1700
Data Index: 872555 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1095. Min Act: -0.1700
Data Index: 3158437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1095. Min Act: -0.1696
Data Index: 1912661 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.0782. Min Act: -0.1700
Data Index: 3070183 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1095. Min Act: -0.1698
Data Index: 4619531 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1095. Min Act: -0.1695
Data Index: 2892976 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1095. Min Act: -0.1700
Data Index: 5469059 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19