Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.2371. Min Act: -0.1700
Data Index: 5723471 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.1433. Min Act: -0.1700
Data Index: 4858270 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.0808. Min Act: -0.1700
Data Index: 213405 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.0496. Min Act: -0.1700
Data Index: 8641250 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.0496. Min Act: -0.1700
Data Index: 4225441 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.0496. Min Act: -0.1700
Data Index: 8740517 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.0183. Min Act: -0.1700
Data Index: 2892367 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.0183. Min Act: -0.1700
Data Index: 2815420 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2371. Min Range: -5.2371
Max Act: 5.0183. Min Act: -0.1700
Data Index: 5924044 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9871. Min Act: -0.1700
Data Index: 8157710 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9871. Min Act: -0.1700
Data Index: 3992524 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9871. Min Act: -0.1700
Data Index: 4443060 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9558. Min Act: -0.1700
Data Index: 5185606 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9871. Min Act: -0.1700
Data Index: 3079844 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9871. Min Act: -0.1700
Data Index: 1198190 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9558. Min Act: -0.1700
Data Index: 7925178 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9558. Min Act: -0.1700
Data Index: 8419702 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9558. Min Act: -0.1700
Data Index: 7059294 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9558. Min Act: -0.1700
Data Index: 1047391 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2371. Min Range: -5.2371
Max Act: 4.9246. Min Act: -0.1700
Data Index: 6220239 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19