Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5079 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0299. Min Range: -5.0299
Max Act: 5.0299. Min Act: -0.1700
Data Index: 5002844 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.9674. Min Act: -0.1700
Data Index: 2246364 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.9049. Min Act: -0.1700
Data Index: 8598220 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.9049. Min Act: -0.1700
Data Index: 4513252 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.8424. Min Act: -0.1700
Data Index: 1663604 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.8111. Min Act: -0.1700
Data Index: 4922268 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.8111. Min Act: -0.1700
Data Index: 1783512 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7799. Min Act: -0.1700
Data Index: 4729331 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7799. Min Act: -0.1700
Data Index: 666951 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 2389162 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 6882446 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7174. Min Act: -0.1700
Data Index: 3467330 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 3824118 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 1277657 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 6381859 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 3634312 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7174. Min Act: -0.1700
Data Index: 4277917 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7174. Min Act: -0.1700
Data Index: 6063537 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6861. Min Act: -0.1700
Data Index: 4840171 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6861. Min Act: -0.1700
Data Index: 257352 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19