Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4073 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.4829. Min Act: -0.1700
Data Index: 4168557 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.3891. Min Act: -0.1700
Data Index: 8165832 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.3579. Min Act: -0.1700
Data Index: 8787443 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.3266. Min Act: -0.1700
Data Index: 1955364 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.2641. Min Act: -0.1700
Data Index: 2226844 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.2016. Min Act: -0.1700
Data Index: 1351091 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.1079. Min Act: -0.1700
Data Index: 8083098 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.0454. Min Act: -0.1700
Data Index: 7427257 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.0454. Min Act: -0.1700
Data Index: 2838304 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.0141. Min Act: -0.1700
Data Index: 5490679 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.0141. Min Act: -0.1700
Data Index: 2304051 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4829. Min Range: -5.4829
Max Act: 5.0141. Min Act: -0.1700
Data Index: 7748881 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4829. Min Range: -5.4829
Max Act: 4.9829. Min Act: -0.1700
Data Index: 1033012 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4829. Min Range: -5.4829
Max Act: 4.9516. Min Act: -0.1700
Data Index: 3756091 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4829. Min Range: -5.4829
Max Act: 4.9516. Min Act: -0.1700
Data Index: 23423 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4829. Min Range: -5.4829
Max Act: 4.9204. Min Act: -0.1700
Data Index: 5096183 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4829. Min Range: -5.4829
Max Act: 4.9204. Min Act: -0.1700
Data Index: 668485 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4829. Min Range: -5.4829
Max Act: 4.9204. Min Act: -0.1700
Data Index: 7848090 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4829. Min Range: -5.4829
Max Act: 4.9204. Min Act: -0.1700
Data Index: 4303345 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4829. Min Range: -5.4829
Max Act: 4.9204. Min Act: -0.1700
Data Index: 3875428 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19