Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1387. Min Range: -6.1387
Max Act: 6.1387. Min Act: -0.1700
Data Index: 2142350 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.9825. Min Act: -0.1700
Data Index: 8332910 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.9200. Min Act: -0.1700
Data Index: 2020742 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.9512. Min Act: -0.1700
Data Index: 5688498 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.9512. Min Act: -0.1700
Data Index: 1296847 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.8887. Min Act: -0.1700
Data Index: 7422167 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.8887. Min Act: -0.1700
Data Index: 7865527 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.8887. Min Act: -0.1700
Data Index: 8697020 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.8887. Min Act: -0.1700
Data Index: 4296901 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.8887. Min Act: -0.1700
Data Index: 5835967 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.8575. Min Act: -0.1700
Data Index: 20314 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.8575. Min Act: -0.1700
Data Index: 2704490 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.8262. Min Act: -0.1700
Data Index: 8549260 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.7950. Min Act: -0.1700
Data Index: 3714143 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.7950. Min Act: -0.1700
Data Index: 2068809 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.7637. Min Act: -0.1700
Data Index: 7032197 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.7637. Min Act: -0.1700
Data Index: 8728664 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.7637. Min Act: -0.1700
Data Index: 2306612 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.7637. Min Act: -0.1700
Data Index: 5194380 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1387. Min Range: -6.1387
Max Act: 5.7637. Min Act: -0.1700
Data Index: 4136699 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19