Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1859. Min Range: -6.1859
Max Act: 6.1859. Min Act: -0.1700
Data Index: 1321074 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1859. Min Range: -6.1859
Max Act: 6.1234. Min Act: -0.1700
Data Index: 5934131 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.8734. Min Act: -0.1700
Data Index: 2399358 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.8734. Min Act: -0.1700
Data Index: 1735246 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.8422. Min Act: -0.1700
Data Index: 7207052 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.8109. Min Act: -0.1700
Data Index: 5224786 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.7484. Min Act: -0.1700
Data Index: 7671071 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.7172. Min Act: -0.1700
Data Index: 202945 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.6859. Min Act: -0.1700
Data Index: 795133 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.6547. Min Act: -0.1700
Data Index: 1286027 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5922. Min Act: -0.1700
Data Index: 931499 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5609. Min Act: -0.1700
Data Index: 6846003 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5922. Min Act: -0.1700
Data Index: 661371 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5609. Min Act: -0.1700
Data Index: 2414183 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5609. Min Act: -0.1700
Data Index: 201287 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5922. Min Act: -0.1700
Data Index: 5156222 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5609. Min Act: -0.1700
Data Index: 7317946 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5609. Min Act: -0.1700
Data Index: 3106076 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5609. Min Act: -0.1700
Data Index: 8572793 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1859. Min Range: -6.1859
Max Act: 5.5609. Min Act: -0.1700
Data Index: 6894693 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19