Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9940. Min Act: -0.1700
Data Index: 2525571 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9627. Min Act: -0.1700
Data Index: 7229175 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.9315. Min Act: -0.1700
Data Index: 4870915 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8690. Min Act: -0.1700
Data Index: 5942246 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8690. Min Act: -0.1700
Data Index: 8300429 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8690. Min Act: -0.1700
Data Index: 8552945 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.8065. Min Act: -0.1700
Data Index: 4635937 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.7752. Min Act: -0.1700
Data Index: 3858308 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.7127. Min Act: -0.1700
Data Index: 2978501 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.7440. Min Act: -0.1700
Data Index: 3448450 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.7127. Min Act: -0.1700
Data Index: 326674 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.7127. Min Act: -0.1700
Data Index: 2765616 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.6815. Min Act: -0.1700
Data Index: 4794352 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.6190. Min Act: -0.1700
Data Index: 3224536 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.6190. Min Act: -0.1700
Data Index: 7851537 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.5877. Min Act: -0.1700
Data Index: 1175568 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.5877. Min Act: -0.1700
Data Index: 255634 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.5877. Min Act: -0.1700
Data Index: 2158397 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.5565. Min Act: -0.1700
Data Index: 2433441 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9940. Min Range: -5.9940
Max Act: 5.5252. Min Act: -0.1700
Data Index: 3327332 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19