Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.4032. Min Act: -0.1700
Data Index: 6864676 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.2720. Min Act: -0.1700
Data Index: 1478032 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.2555. Min Act: -0.1700
Data Index: 6143208 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.2555. Min Act: -0.1700
Data Index: 7393067 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.2224. Min Act: -0.1700
Data Index: 5291763 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.2059. Min Act: -0.1700
Data Index: 6095130 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1727. Min Act: -0.1700
Data Index: 8683742 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1727. Min Act: -0.1700
Data Index: 3906736 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1560. Min Act: -0.1700
Data Index: 3871942 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1560. Min Act: -0.1700
Data Index: 6908295 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1477. Min Act: -0.1700
Data Index: 4065994 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1477. Min Act: -0.1700
Data Index: 959689 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1393. Min Act: -0.1700
Data Index: 136464 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1310. Min Act: -0.1700
Data Index: 7424125 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1393. Min Act: -0.1700
Data Index: 3774578 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1226. Min Act: -0.1695
Data Index: 5403016 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1143. Min Act: -0.1700
Data Index: 1527081 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1310. Min Act: -0.1700
Data Index: 1703090 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1226. Min Act: -0.1700
Data Index: 4091246 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4032. Min Range: -2.4032
Max Act: 2.1226. Min Act: -0.1699
Data Index: 4184306 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19