Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1994 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.9235. Min Act: -0.1700
Data Index: 7753494 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.3610. Min Act: -0.1700
Data Index: 4900892 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.2673. Min Act: -0.1700
Data Index: 5379897 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.2360. Min Act: -0.1700
Data Index: 5874343 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.1735. Min Act: -0.1700
Data Index: 5206045 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.1735. Min Act: -0.1700
Data Index: 57254 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.1110. Min Act: -0.1700
Data Index: 2270131 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.1110. Min Act: -0.1700
Data Index: 7413970 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.0798. Min Act: -0.1700
Data Index: 918046 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9235. Min Range: -7.9235
Max Act: 7.0485. Min Act: -0.1700
Data Index: 7901258 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.9860. Min Act: -0.1700
Data Index: 5043529 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.9860. Min Act: -0.1700
Data Index: 7688299 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.9548. Min Act: -0.1700
Data Index: 5209110 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.9235. Min Act: -0.1700
Data Index: 7080473 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.8923. Min Act: -0.1700
Data Index: 1065430 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.8923. Min Act: -0.1700
Data Index: 7705390 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.8923. Min Act: -0.1700
Data Index: 4490896 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.8923. Min Act: -0.1700
Data Index: 7433851 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.8610. Min Act: -0.1700
Data Index: 572512 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9235. Min Range: -7.9235
Max Act: 6.8298. Min Act: -0.1700
Data Index: 6511902 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19