Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.8329. Min Act: -0.1700
Data Index: 7617676 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.6454. Min Act: -0.1700
Data Index: 7478339 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.6767. Min Act: -0.1700
Data Index: 4658729 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.6767. Min Act: -0.1700
Data Index: 2336830 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.6767. Min Act: -0.1700
Data Index: 2537209 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.6142. Min Act: -0.1699
Data Index: 4995038 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.6142. Min Act: -0.1700
Data Index: 1113486 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.6454. Min Act: -0.1700
Data Index: 4573485 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5829. Min Act: -0.1700
Data Index: 2341880 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5829. Min Act: -0.1700
Data Index: 4778074 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5517. Min Act: -0.1700
Data Index: 242591 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5829. Min Act: -0.1700
Data Index: 8133948 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5517. Min Act: -0.1700
Data Index: 6151831 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5204. Min Act: -0.1700
Data Index: 6597799 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5204. Min Act: -0.1700
Data Index: 4274831 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5204. Min Act: -0.1700
Data Index: 5822632 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5204. Min Act: -0.1700
Data Index: 7478338 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5517. Min Act: -0.1700
Data Index: 2303658 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5204. Min Act: -0.1700
Data Index: 3550504 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8329. Min Range: -5.8329
Max Act: 5.5204. Min Act: -0.1700
Data Index: 1694852 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19