Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2445. Min Range: -4.2445
Max Act: 4.2445. Min Act: -0.1700
Data Index: 871216 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.9944. Min Act: -0.1700
Data Index: 450193 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.9319. Min Act: -0.1700
Data Index: 6416202 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.9319. Min Act: -0.1700
Data Index: 2734488 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.9006. Min Act: -0.1700
Data Index: 1633033 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.8068. Min Act: -0.1700
Data Index: 6627588 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.8068. Min Act: -0.1700
Data Index: 7475182 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.7912. Min Act: -0.1700
Data Index: 4951061 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.7286. Min Act: -0.1700
Data Index: 1738674 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.7286. Min Act: -0.1700
Data Index: 4968556 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.7130. Min Act: -0.1700
Data Index: 3919995 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.7130. Min Act: -0.1700
Data Index: 5600456 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.6817. Min Act: -0.1700
Data Index: 1408929 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.6973. Min Act: -0.1700
Data Index: 2250843 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.6973. Min Act: -0.1700
Data Index: 5226180 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.6973. Min Act: -0.1700
Data Index: 2716069 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.6973. Min Act: -0.1700
Data Index: 5298332 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.6973. Min Act: -0.1700
Data Index: 5865166 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.6660. Min Act: -0.1700
Data Index: 4240975 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2445. Min Range: -4.2445
Max Act: 3.6660. Min Act: -0.1700
Data Index: 7055520 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19