Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.9619. Min Act: -0.1700
Data Index: 1435116 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.9619. Min Act: -0.1700
Data Index: 4690742 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.9619. Min Act: -0.1700
Data Index: 2754746 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.9306. Min Act: -0.1700
Data Index: 774521 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.9306. Min Act: -0.1700
Data Index: 2578023 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8368. Min Act: -0.1700
Data Index: 7449788 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8368. Min Act: -0.1700
Data Index: 8282 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8368. Min Act: -0.1700
Data Index: 2992324 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8055. Min Act: -0.1700
Data Index: 2149683 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8368. Min Act: -0.1700
Data Index: 4469359 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8055. Min Act: -0.1700
Data Index: 788795 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8055. Min Act: -0.1700
Data Index: 2376735 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2993625 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.7742. Min Act: -0.1700
Data Index: 137732 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8055. Min Act: -0.1700
Data Index: 600961 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.8055. Min Act: -0.1700
Data Index: 3399690 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.7742. Min Act: -0.1700
Data Index: 5059786 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.7430. Min Act: -0.1700
Data Index: 4103778 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.7430. Min Act: -0.1700
Data Index: 4469358 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9619. Min Range: -3.9619
Max Act: 3.7430. Min Act: -0.1700
Data Index: 3696181 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19