Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4929. Min Range: -8.4929
Max Act: 8.4929. Min Act: -0.1700
Data Index: 8620199 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4929. Min Range: -8.4929
Max Act: 8.3054. Min Act: -0.1700
Data Index: 6107067 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4929. Min Range: -8.4929
Max Act: 8.1491. Min Act: -0.1700
Data Index: 2548212 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4929. Min Range: -8.4929
Max Act: 8.0241. Min Act: -0.1700
Data Index: 4107336 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.9929. Min Act: -0.1700
Data Index: 4753334 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.9616. Min Act: -0.1700
Data Index: 4866919 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.9929. Min Act: -0.1700
Data Index: 3765272 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.9304. Min Act: -0.1700
Data Index: 2358717 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.8991. Min Act: -0.1700
Data Index: 3146611 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.8054. Min Act: -0.1700
Data Index: 8178216 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.8054. Min Act: -0.1700
Data Index: 3063883 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.8054. Min Act: -0.1700
Data Index: 726048 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.7741. Min Act: -0.1700
Data Index: 6491665 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.7429. Min Act: -0.1700
Data Index: 60342 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.7429. Min Act: -0.1700
Data Index: 7777949 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.7116. Min Act: -0.1700
Data Index: 7861458 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.7116. Min Act: -0.1700
Data Index: 7349806 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.7116. Min Act: -0.1700
Data Index: 3298917 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.7116. Min Act: -0.1700
Data Index: 447432 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4929. Min Range: -8.4929
Max Act: 7.6804. Min Act: -0.1700
Data Index: 4753333 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19