Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4823 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.8371. Min Act: -0.1700
Data Index: 569002 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.8371. Min Act: -0.1700
Data Index: 1875112 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.7433. Min Act: -0.1700
Data Index: 2498091 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.7433. Min Act: -0.1700
Data Index: 1875105 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.7433. Min Act: -0.1700
Data Index: 1310308 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.6808. Min Act: -0.1700
Data Index: 5210015 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.6496. Min Act: -0.1700
Data Index: 799697 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.5871. Min Act: -0.1700
Data Index: 2678149 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.5558. Min Act: -0.1700
Data Index: 2326296 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.5558. Min Act: -0.1700
Data Index: 6965819 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.4933. Min Act: -0.1700
Data Index: 7073371 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.4933. Min Act: -0.1700
Data Index: 222006 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.5246. Min Act: -0.1700
Data Index: 5302388 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.4933. Min Act: -0.1700
Data Index: 2689817 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.4621. Min Act: -0.1700
Data Index: 7087588 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.4933. Min Act: -0.1700
Data Index: 6965818 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.4933. Min Act: -0.1700
Data Index: 541071 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.4621. Min Act: -0.1700
Data Index: 4845192 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.4621. Min Act: -0.1700
Data Index: 1612855 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8371. Min Range: -4.8371
Max Act: 4.4621. Min Act: -0.1700
Data Index: 710187 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19