Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1556 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0309. Min Range: -5.0309
Max Act: 5.0309. Min Act: -0.1700
Data Index: 6603275 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.9684. Min Act: -0.1700
Data Index: 3540583 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.9371. Min Act: -0.1700
Data Index: 3898687 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.8746. Min Act: -0.1700
Data Index: 7093358 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.7809. Min Act: -0.1700
Data Index: 6958236 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.7184. Min Act: -0.1700
Data Index: 6306998 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.7184. Min Act: -0.1700
Data Index: 4156547 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.7184. Min Act: -0.1700
Data Index: 3646293 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6871. Min Act: -0.1700
Data Index: 2715644 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6871. Min Act: -0.1700
Data Index: 4592935 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6871. Min Act: -0.1700
Data Index: 3231663 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6559. Min Act: -0.1700
Data Index: 8754439 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6559. Min Act: -0.1700
Data Index: 5265632 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6559. Min Act: -0.1700
Data Index: 8789205 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6246. Min Act: -0.1700
Data Index: 3827802 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6246. Min Act: -0.1700
Data Index: 2293324 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6246. Min Act: -0.1700
Data Index: 6637877 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.6246. Min Act: -0.1700
Data Index: 5473331 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.5934. Min Act: -0.1700
Data Index: 7530378 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0309. Min Range: -5.0309
Max Act: 4.5934. Min Act: -0.1700
Data Index: 3557878 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19