Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.8058. Min Act: -0.1699
Data Index: 8378028 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.6808. Min Act: -0.1700
Data Index: 3337186 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.6183. Min Act: -0.1700
Data Index: 7868542 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.6183. Min Act: -0.1700
Data Index: 5748464 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.6183. Min Act: -0.1700
Data Index: 5186603 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.6183. Min Act: -0.1699
Data Index: 6942334 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5871. Min Act: -0.1700
Data Index: 8766123 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5246. Min Act: -0.1700
Data Index: 5529289 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5558. Min Act: -0.1695
Data Index: 6772588 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5558. Min Act: -0.1700
Data Index: 1956908 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5558. Min Act: -0.1700
Data Index: 2619435 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5558. Min Act: -0.1700
Data Index: 8179126 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5246. Min Act: -0.1700
Data Index: 1492891 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5558. Min Act: -0.1664
Data Index: 370385 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5246. Min Act: -0.1699
Data Index: 3166869 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5246. Min Act: -0.1699
Data Index: 3343786 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5246. Min Act: -0.1700
Data Index: 6422680 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5246. Min Act: -0.1699
Data Index: 2217750 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5246. Min Act: -0.1690
Data Index: 4065908 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8058. Min Range: -4.8058
Max Act: 4.5246. Min Act: -0.1660
Data Index: 6925142 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19