Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.5287. Min Act: -0.1700
Data Index: 3797926 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.4974. Min Act: -0.1700
Data Index: 8746388 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.4349. Min Act: -0.1700
Data Index: 3173176 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.3412. Min Act: -0.1700
Data Index: 1952190 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.3099. Min Act: -0.1700
Data Index: 7401495 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.3099. Min Act: -0.1700
Data Index: 52617 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.2787. Min Act: -0.1700
Data Index: 5554227 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.3099. Min Act: -0.1700
Data Index: 5509353 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.2787. Min Act: -0.1700
Data Index: 8326426 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.2787. Min Act: -0.1700
Data Index: 5052076 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.2474. Min Act: -0.1700
Data Index: 6435744 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.2162. Min Act: -0.1700
Data Index: 2448176 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.2162. Min Act: -0.1700
Data Index: 4338232 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1537. Min Act: -0.1700
Data Index: 8048960 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.2162. Min Act: -0.1700
Data Index: 8283101 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1537. Min Act: -0.1700
Data Index: 2834696 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1537. Min Act: -0.1700
Data Index: 6866527 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1537. Min Act: -0.1700
Data Index: 2381726 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1224. Min Act: -0.1700
Data Index: 7775980 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5287. Min Range: -6.5287
Max Act: 6.1224. Min Act: -0.1700
Data Index: 5461870 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19