Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1059 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6709. Min Range: -9.6709
Max Act: 9.6709. Min Act: -0.1700
Data Index: 4404265 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6709. Min Range: -9.6709
Max Act: 9.6709. Min Act: -0.1700
Data Index: 6650953 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6709. Min Range: -9.6709
Max Act: 9.1709. Min Act: -0.1700
Data Index: 3079962 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6709. Min Range: -9.6709
Max Act: 9.1709. Min Act: -0.1700
Data Index: 8831875 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6709. Min Range: -9.6709
Max Act: 9.1709. Min Act: -0.1700
Data Index: 1620674 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6709. Min Range: -9.6709
Max Act: 9.0459. Min Act: -0.1700
Data Index: 4774909 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.9834. Min Act: -0.1700
Data Index: 7561102 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.9834. Min Act: -0.1700
Data Index: 8533693 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.9209. Min Act: -0.1700
Data Index: 7085140 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.9209. Min Act: -0.1700
Data Index: 262739 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.8584. Min Act: -0.1700
Data Index: 2278416 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.8584. Min Act: -0.1700
Data Index: 2318668 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.9209. Min Act: -0.1700
Data Index: 7251423 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.8584. Min Act: -0.1700
Data Index: 2609457 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.8584. Min Act: -0.1700
Data Index: 51012 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.7959. Min Act: -0.1700
Data Index: 4963983 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.7959. Min Act: -0.1700
Data Index: 3546929 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.7959. Min Act: -0.1700
Data Index: 6313369 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.8584. Min Act: -0.1700
Data Index: 741484 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6709. Min Range: -9.6709
Max Act: 8.7959. Min Act: -0.1700
Data Index: 8494611 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19