Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3169 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.5228. Min Act: -0.1700
Data Index: 2519705 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.2405. Min Act: -0.1700
Data Index: 2891393 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.2248. Min Act: -0.1700
Data Index: 2463016 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1934. Min Act: -0.1700
Data Index: 2122860 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.2091. Min Act: -0.1700
Data Index: 3252988 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1934. Min Act: -0.1700
Data Index: 582425 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1776. Min Act: -0.1700
Data Index: 7419469 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1934. Min Act: -0.1700
Data Index: 7436627 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1619. Min Act: -0.1700
Data Index: 405236 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1619. Min Act: -0.1700
Data Index: 320930 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1619. Min Act: -0.1700
Data Index: 539322 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1462. Min Act: -0.1700
Data Index: 3939921 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1462. Min Act: -0.1700
Data Index: 3040988 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1462. Min Act: -0.1700
Data Index: 8704521 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1462. Min Act: -0.1700
Data Index: 6983254 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1462. Min Act: -0.1700
Data Index: 6275958 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1462. Min Act: -0.1700
Data Index: 5551121 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1462. Min Act: -0.1700
Data Index: 2251907 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1462. Min Act: -0.1700
Data Index: 5278349 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5228. Min Range: -3.5228
Max Act: 3.1304. Min Act: -0.1700
Data Index: 1793799 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19