Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3142 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.6164. Min Act: -0.1700
Data Index: 7592609 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.4914. Min Act: -0.1700
Data Index: 2712454 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.4601. Min Act: -0.1700
Data Index: 7222271 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.4601. Min Act: -0.1700
Data Index: 303702 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.4601. Min Act: -0.1700
Data Index: 7135712 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3976. Min Act: -0.1700
Data Index: 3081413 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3976. Min Act: -0.1700
Data Index: 3949743 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3351. Min Act: -0.1700
Data Index: 6426022 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3351. Min Act: -0.1700
Data Index: 866081 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3351. Min Act: -0.1700
Data Index: 7252791 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3039. Min Act: -0.1700
Data Index: 7241725 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3039. Min Act: -0.1700
Data Index: 1101470 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3039. Min Act: -0.1700
Data Index: 3491448 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3039. Min Act: -0.1700
Data Index: 8671832 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3039. Min Act: -0.1700
Data Index: 405162 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.2414. Min Act: -0.1700
Data Index: 1863986 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.2726. Min Act: -0.1700
Data Index: 6636575 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.3039. Min Act: -0.1700
Data Index: 8715052 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.2726. Min Act: -0.1700
Data Index: 1488333 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6164. Min Range: -5.6164
Max Act: 5.2414. Min Act: -0.1700
Data Index: 7705892 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19