Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.8522. Min Act: -0.1700
Data Index: 1175534 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.7897. Min Act: -0.1700
Data Index: 1591639 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.3522. Min Act: -0.1700
Data Index: 6899982 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.3522. Min Act: -0.1700
Data Index: 2419285 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.2272. Min Act: -0.1700
Data Index: 4624642 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.2272. Min Act: -0.1700
Data Index: 519401 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.2272. Min Act: -0.1700
Data Index: 3477186 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.2272. Min Act: -0.1700
Data Index: 2408972 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.1647. Min Act: -0.1700
Data Index: 2704396 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.1647. Min Act: -0.1700
Data Index: 2270546 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.1022. Min Act: -0.1700
Data Index: 221536 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.1022. Min Act: -0.1700
Data Index: 5381648 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.1647. Min Act: -0.1700
Data Index: 1041274 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.1022. Min Act: -0.1700
Data Index: 8690991 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.1022. Min Act: -0.1700
Data Index: 1759506 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.1022. Min Act: -0.1700
Data Index: 2840504 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.0397. Min Act: -0.1700
Data Index: 1570083 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.0397. Min Act: -0.1700
Data Index: 4572018 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.0397. Min Act: -0.1700
Data Index: 7514851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8522. Min Range: -8.8522
Max Act: 8.0397. Min Act: -0.1700
Data Index: 8298492 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19