Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1638 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.4487. Min Act: -0.1700
Data Index: 2317575 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.1987. Min Act: -0.1700
Data Index: 8243826 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.1674. Min Act: -0.1700
Data Index: 924998 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.1362. Min Act: -0.1700
Data Index: 7725230 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.1362. Min Act: -0.1700
Data Index: 7722665 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.1362. Min Act: -0.1700
Data Index: 5168353 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.1362. Min Act: -0.1700
Data Index: 6968437 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.1049. Min Act: -0.1700
Data Index: 7035377 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0737. Min Act: -0.1700
Data Index: 296390 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0737. Min Act: -0.1700
Data Index: 1840175 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0424. Min Act: -0.1700
Data Index: 2637721 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0424. Min Act: -0.1700
Data Index: 4244019 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0424. Min Act: -0.1700
Data Index: 5387764 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0424. Min Act: -0.1700
Data Index: 6498039 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0112. Min Act: -0.1700
Data Index: 5288924 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0112. Min Act: -0.1700
Data Index: 742897 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0112. Min Act: -0.1700
Data Index: 7200551 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0112. Min Act: -0.1700
Data Index: 7432107 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0424. Min Act: -0.1700
Data Index: 501207 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4487. Min Range: -5.4487
Max Act: 5.0424. Min Act: -0.1700
Data Index: 5076659 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19