Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4190 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.1381. Min Range: -16.1381
Max Act: 16.1381. Min Act: -0.1700
Data Index: 5120733 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.7630. Min Act: -0.1700
Data Index: 3363994 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.6380. Min Act: -0.1700
Data Index: 657085 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.6380. Min Act: -0.1700
Data Index: 6837483 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.6380. Min Act: -0.1700
Data Index: 7034090 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.4505. Min Act: -0.1700
Data Index: 3235342 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.5130. Min Act: -0.1700
Data Index: 6666183 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.5130. Min Act: -0.1700
Data Index: 190171 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.4505. Min Act: -0.1700
Data Index: 7439982 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.4505. Min Act: -0.1700
Data Index: 5533425 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.4505. Min Act: -0.1700
Data Index: 402696 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.4505. Min Act: -0.1700
Data Index: 111129 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.3880. Min Act: -0.1700
Data Index: 3110854 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.4505. Min Act: -0.1700
Data Index: 5950028 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.3880. Min Act: -0.1700
Data Index: 2319857 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.3880. Min Act: -0.1700
Data Index: 4146516 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.3880. Min Act: -0.1700
Data Index: 3654374 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.3255. Min Act: -0.1700
Data Index: 3648168 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.3255. Min Act: -0.1700
Data Index: 1715341 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.1381. Min Range: -16.1381
Max Act: 15.3255. Min Act: -0.1700
Data Index: 2479097 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19