Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5738 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.8814. Min Act: -0.1700
Data Index: 6437529 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.8179. Min Act: -0.1700
Data Index: 6757125 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.8020. Min Act: -0.1700
Data Index: 3256607 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7701. Min Act: -0.1700
Data Index: 5315545 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.8020. Min Act: -0.1700
Data Index: 5451475 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7701. Min Act: -0.1700
Data Index: 2448732 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7541. Min Act: -0.1700
Data Index: 7315983 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7701. Min Act: -0.1700
Data Index: 7561227 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7541. Min Act: -0.1700
Data Index: 650206 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7541. Min Act: -0.1700
Data Index: 1312113 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7382. Min Act: -0.1700
Data Index: 2416423 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7541. Min Act: -0.1700
Data Index: 5530828 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7222. Min Act: -0.1700
Data Index: 1088319 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7222. Min Act: -0.1700
Data Index: 5045816 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7222. Min Act: -0.1700
Data Index: 4508207 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7062. Min Act: -0.1700
Data Index: 4388659 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7062. Min Act: -0.1700
Data Index: 502230 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7062. Min Act: -0.1700
Data Index: 5640017 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7062. Min Act: -0.1700
Data Index: 6013144 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8814. Min Range: -2.8814
Max Act: 2.7062. Min Act: -0.1700
Data Index: 5140624 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19