Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.6838. Min Act: -0.1700
Data Index: 1002771 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.6525. Min Act: -0.1700
Data Index: 1002772 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.6525. Min Act: -0.1700
Data Index: 614590 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.5275. Min Act: -0.1700
Data Index: 5145520 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.5275. Min Act: -0.1700
Data Index: 1652239 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.4963. Min Act: -0.1700
Data Index: 1380369 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.4025. Min Act: -0.1700
Data Index: 2159760 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.4025. Min Act: -0.1700
Data Index: 1198139 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.4338. Min Act: -0.1700
Data Index: 2156498 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.3713. Min Act: -0.1700
Data Index: 3233334 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.3400. Min Act: -0.1700
Data Index: 4298847 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.3400. Min Act: -0.1700
Data Index: 7688725 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.2775. Min Act: -0.1700
Data Index: 3706592 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.2463. Min Act: -0.1700
Data Index: 7783355 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.2463. Min Act: -0.1700
Data Index: 447955 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.2463. Min Act: -0.1700
Data Index: 8794196 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.1838. Min Act: -0.1700
Data Index: 1628996 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.1838. Min Act: -0.1700
Data Index: 5982041 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.2150. Min Act: -0.1700
Data Index: 4298834 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6838. Min Range: -5.6838
Max Act: 5.2150. Min Act: -0.1700
Data Index: 2853552 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19