Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.5425. Min Act: -0.1700
Data Index: 6136685 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.4800. Min Act: -0.1700
Data Index: 3392552 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.4487. Min Act: -0.1700
Data Index: 1935255 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.4800. Min Act: -0.1700
Data Index: 5072661 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.4487. Min Act: -0.1700
Data Index: 8186509 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.4487. Min Act: -0.1700
Data Index: 4460066 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3550. Min Act: -0.1700
Data Index: 1417270 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3862. Min Act: -0.1700
Data Index: 3442227 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3862. Min Act: -0.1700
Data Index: 8816292 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3550. Min Act: -0.1700
Data Index: 2546557 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3237. Min Act: -0.1700
Data Index: 6720993 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3550. Min Act: -0.1700
Data Index: 7862354 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3550. Min Act: -0.1700
Data Index: 7312078 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3550. Min Act: -0.1700
Data Index: 7797495 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3237. Min Act: -0.1700
Data Index: 4033788 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3550. Min Act: -0.1700
Data Index: 757689 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3237. Min Act: -0.1700
Data Index: 7061079 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3237. Min Act: -0.1700
Data Index: 6974344 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3237. Min Act: -0.1700
Data Index: 4304292 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5425. Min Range: -6.5425
Max Act: 6.3237. Min Act: -0.1700
Data Index: 2002663 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19