Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5487 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.8222. Min Act: -0.1700
Data Index: 4645252 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.5410. Min Act: -0.1700
Data Index: 6129559 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.5410. Min Act: -0.1700
Data Index: 1290770 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.4785. Min Act: -0.1700
Data Index: 1322565 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.4785. Min Act: -0.1700
Data Index: 3604693 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.4785. Min Act: -0.1700
Data Index: 8014199 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.3847. Min Act: -0.1700
Data Index: 527908 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.3847. Min Act: -0.1700
Data Index: 535261 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.3222. Min Act: -0.1700
Data Index: 2623186 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.2910. Min Act: -0.1700
Data Index: 8461029 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.3222. Min Act: -0.1700
Data Index: 5315379 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.3222. Min Act: -0.1700
Data Index: 2983411 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.2910. Min Act: -0.1700
Data Index: 7432323 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.2910. Min Act: -0.1700
Data Index: 4143874 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.2597. Min Act: -0.1700
Data Index: 5165979 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.2597. Min Act: -0.1700
Data Index: 3395397 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.2597. Min Act: -0.1700
Data Index: 8726791 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.2285. Min Act: -0.1700
Data Index: 6487174 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.1972. Min Act: -0.1700
Data Index: 1493641 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8222. Min Range: -5.8222
Max Act: 5.2285. Min Act: -0.1700
Data Index: 2618680 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19