Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1061 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.7432. Min Act: -0.1700
Data Index: 1423957 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.5245. Min Act: -0.1700
Data Index: 6088504 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.5245. Min Act: -0.1700
Data Index: 8684660 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.5245. Min Act: -0.1700
Data Index: 203868 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.4932. Min Act: -0.1700
Data Index: 4712554 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.4932. Min Act: -0.1700
Data Index: 2419601 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.4620. Min Act: -0.1700
Data Index: 3624749 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.4307. Min Act: -0.1700
Data Index: 4712555 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.4932. Min Act: -0.1700
Data Index: 5677520 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.3994. Min Act: -0.1700
Data Index: 227323 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.4307. Min Act: -0.1700
Data Index: 3068813 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.3994. Min Act: -0.1700
Data Index: 3352919 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.4307. Min Act: -0.1700
Data Index: 2813269 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.3994. Min Act: -0.1700
Data Index: 2435100 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.3682. Min Act: -0.1700
Data Index: 4252189 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.3682. Min Act: -0.1700
Data Index: 4282695 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.3682. Min Act: -0.1700
Data Index: 8323770 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.3369. Min Act: -0.1700
Data Index: 4070199 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.3369. Min Act: -0.1700
Data Index: 5778659 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7432. Min Range: -4.7432
Max Act: 4.3369. Min Act: -0.1700
Data Index: 5961645 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19