Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3809 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.8984. Min Act: -0.1700
Data Index: 8775745 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.8359. Min Act: -0.1700
Data Index: 6417092 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.7734. Min Act: -0.1700
Data Index: 2262946 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.7109. Min Act: -0.1700
Data Index: 1460619 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.6484. Min Act: -0.1700
Data Index: 1790367 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5859. Min Act: -0.1700
Data Index: 2827669 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.6484. Min Act: -0.1700
Data Index: 6142165 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.6484. Min Act: -0.1700
Data Index: 5785503 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.6484. Min Act: -0.1700
Data Index: 8412732 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.6484. Min Act: -0.1700
Data Index: 4832617 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5859. Min Act: -0.1700
Data Index: 1378904 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5859. Min Act: -0.1700
Data Index: 2703836 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5859. Min Act: -0.1700
Data Index: 7012511 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5859. Min Act: -0.1700
Data Index: 4696006 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5234. Min Act: -0.1700
Data Index: 3590395 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5234. Min Act: -0.1700
Data Index: 6970217 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5234. Min Act: -0.1700
Data Index: 8002896 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5234. Min Act: -0.1700
Data Index: 2396691 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5234. Min Act: -0.1700
Data Index: 8083527 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8984. Min Range: -7.8984
Max Act: 7.5859. Min Act: -0.1700
Data Index: 3761332 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19