Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1557 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.4930. Min Act: -0.1700
Data Index: 250716 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.4930. Min Act: -0.1700
Data Index: 2259688 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.4617. Min Act: -0.1700
Data Index: 3393049 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3992. Min Act: -0.1700
Data Index: 4911465 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3367. Min Act: -0.1700
Data Index: 5646661 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3055. Min Act: -0.1700
Data Index: 4435549 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3367. Min Act: -0.1700
Data Index: 7696007 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3055. Min Act: -0.1700
Data Index: 419290 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3055. Min Act: -0.1700
Data Index: 1943037 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3367. Min Act: -0.1700
Data Index: 7218192 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3055. Min Act: -0.1700
Data Index: 3632343 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3367. Min Act: -0.1700
Data Index: 5488935 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.2742. Min Act: -0.1700
Data Index: 7386625 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.2742. Min Act: -0.1700
Data Index: 8648266 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.2742. Min Act: -0.1700
Data Index: 2941779 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.3055. Min Act: -0.1700
Data Index: 3346703 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.2430. Min Act: -0.1700
Data Index: 4335501 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.2117. Min Act: -0.1700
Data Index: 8142549 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.2430. Min Act: -0.1700
Data Index: 5042600 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4930. Min Range: -6.4930
Max Act: 6.2430. Min Act: -0.1700
Data Index: 5096398 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19