Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2595. Min Range: -2.2595
Max Act: 2.2595. Min Act: -0.1700
Data Index: 7166665 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2595. Min Range: -2.2595
Max Act: 2.1767. Min Act: -0.1700
Data Index: 8081139 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2595. Min Range: -2.2595
Max Act: 2.0091. Min Act: -0.1700
Data Index: 5722930 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2595. Min Range: -2.2595
Max Act: 2.0091. Min Act: -0.1700
Data Index: 7560434 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2595. Min Range: -2.2595
Max Act: 2.0260. Min Act: -0.1700
Data Index: 6657491 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2595. Min Range: -2.2595
Max Act: 2.0091. Min Act: -0.1700
Data Index: 8098740 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.9753. Min Act: -0.1700
Data Index: 7505793 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.9753. Min Act: -0.1700
Data Index: 1417269 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.9244. Min Act: -0.1700
Data Index: 1408887 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.9244. Min Act: -0.1700
Data Index: 4522837 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.9244. Min Act: -0.1700
Data Index: 4729146 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.9244. Min Act: -0.1700
Data Index: 3543761 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.9244. Min Act: -0.1700
Data Index: 8548279 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.8903. Min Act: -0.1700
Data Index: 2761829 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.8903. Min Act: -0.1700
Data Index: 2334147 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.8903. Min Act: -0.1700
Data Index: 336528 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.8903. Min Act: -0.1700
Data Index: 8539636 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.8903. Min Act: -0.1700
Data Index: 1564401 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.8903. Min Act: -0.1700
Data Index: 1056729 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2595. Min Range: -2.2595
Max Act: 1.8903. Min Act: -0.1700
Data Index: 1759973 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19