Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6221 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.5662. Min Act: -0.1700
Data Index: 2513913 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.5037. Min Act: -0.1700
Data Index: 1458639 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.4724. Min Act: -0.1700
Data Index: 2721177 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.4724. Min Act: -0.1700
Data Index: 7634228 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.4412. Min Act: -0.1700
Data Index: 8349897 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.4099. Min Act: -0.1700
Data Index: 6876090 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.3787. Min Act: -0.1700
Data Index: 6955484 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.3474. Min Act: -0.1700
Data Index: 4371819 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2849. Min Act: -0.1700
Data Index: 5047597 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2849. Min Act: -0.1700
Data Index: 1875004 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2849. Min Act: -0.1700
Data Index: 4583453 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2537. Min Act: -0.1700
Data Index: 521 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2537. Min Act: -0.1700
Data Index: 2288758 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2224. Min Act: -0.1700
Data Index: 2985068 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2224. Min Act: -0.1700
Data Index: 752571 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2224. Min Act: -0.1700
Data Index: 2680561 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.1599. Min Act: -0.1700
Data Index: 3227974 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.1599. Min Act: -0.1700
Data Index: 715864 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.1599. Min Act: -0.1700
Data Index: 7552256 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.1912. Min Act: -0.1700
Data Index: 1717672 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19