Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1846 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.3674. Min Act: -0.1700
Data Index: 8142609 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.3517. Min Act: -0.1700
Data Index: 3112576 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.3360. Min Act: -0.1700
Data Index: 5478115 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.3203. Min Act: -0.1700
Data Index: 7156845 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.2575. Min Act: -0.1700
Data Index: 4967734 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.2732. Min Act: -0.1700
Data Index: 170701 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.2418. Min Act: -0.1700
Data Index: 4210162 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.2418. Min Act: -0.1700
Data Index: 5445704 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.2418. Min Act: -0.1700
Data Index: 7333659 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.2418. Min Act: -0.1700
Data Index: 75745 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.2104. Min Act: -0.1700
Data Index: 3420295 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.2104. Min Act: -0.1700
Data Index: 8172809 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.1946. Min Act: -0.1700
Data Index: 5359903 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.2104. Min Act: -0.1700
Data Index: 381056 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.1946. Min Act: -0.1700
Data Index: 4889879 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.1946. Min Act: -0.1700
Data Index: 323008 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.1789. Min Act: -0.1700
Data Index: 4502241 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.1789. Min Act: -0.1700
Data Index: 4155157 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.1789. Min Act: -0.1700
Data Index: 1514854 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3674. Min Range: -3.3674
Max Act: 3.1632. Min Act: -0.1700
Data Index: 6966299 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19