Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1989 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.9576. Min Act: -0.1700
Data Index: 288417 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.9263. Min Act: -0.1700
Data Index: 8274653 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.9263. Min Act: -0.1700
Data Index: 7573794 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.9263. Min Act: -0.1700
Data Index: 5874156 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8326. Min Act: -0.1700
Data Index: 6740586 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8326. Min Act: -0.1700
Data Index: 2882111 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8638. Min Act: -0.1700
Data Index: 8408640 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8326. Min Act: -0.1700
Data Index: 6049780 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8013. Min Act: -0.1700
Data Index: 4814046 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8013. Min Act: -0.1700
Data Index: 765458 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8013. Min Act: -0.1700
Data Index: 5492239 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8013. Min Act: -0.1700
Data Index: 7295892 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8013. Min Act: -0.1700
Data Index: 6942380 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.8013. Min Act: -0.1700
Data Index: 5688047 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.7701. Min Act: -0.1700
Data Index: 1118634 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.7701. Min Act: -0.1700
Data Index: 7999598 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.7701. Min Act: -0.1700
Data Index: 2293465 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.7388. Min Act: -0.1700
Data Index: 2153499 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.7388. Min Act: -0.1700
Data Index: 6235389 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9576. Min Range: -6.9576
Max Act: 6.7388. Min Act: -0.1700
Data Index: 7827539 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19