Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.5637. Min Act: -0.1700
Data Index: 1605134 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.3762. Min Act: -0.1700
Data Index: 3400045 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.4387. Min Act: -0.1700
Data Index: 3757316 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.3762. Min Act: -0.1700
Data Index: 3790270 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.3449. Min Act: -0.1700
Data Index: 5148200 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.2824. Min Act: -0.1700
Data Index: 1555879 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.2824. Min Act: -0.1700
Data Index: 4193302 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.2512. Min Act: -0.1700
Data Index: 3937885 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.2824. Min Act: -0.1700
Data Index: 4360179 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.2512. Min Act: -0.1700
Data Index: 8347639 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.2199. Min Act: -0.1700
Data Index: 4857016 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.1574. Min Act: -0.1700
Data Index: 1581562 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.1574. Min Act: -0.1700
Data Index: 8799910 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.1574. Min Act: -0.1700
Data Index: 3296702 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.1574. Min Act: -0.1700
Data Index: 6409567 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.1262. Min Act: -0.1700
Data Index: 4209599 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.1574. Min Act: -0.1700
Data Index: 7917668 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.0949. Min Act: -0.1700
Data Index: 4935182 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.1262. Min Act: -0.1700
Data Index: 5772852 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5637. Min Range: -7.5637
Max Act: 7.0637. Min Act: -0.1700
Data Index: 4192657 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19