Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5017 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3543. Min Range: -10.3543
Max Act: 10.3543. Min Act: -0.1700
Data Index: 1665168 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3543. Min Range: -10.3543
Max Act: 10.1668. Min Act: -0.1700
Data Index: 8120072 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3543. Min Range: -10.3543
Max Act: 10.0418. Min Act: -0.1700
Data Index: 8325385 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3543. Min Range: -10.3543
Max Act: 10.0418. Min Act: -0.1700
Data Index: 8251723 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.9793. Min Act: -0.1700
Data Index: 4008948 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.9793. Min Act: -0.1700
Data Index: 3317302 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.9168. Min Act: -0.1700
Data Index: 7878762 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.7293. Min Act: -0.1700
Data Index: 2173569 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.7293. Min Act: -0.1700
Data Index: 8530199 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.7293. Min Act: -0.1700
Data Index: 3578415 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.7293. Min Act: -0.1700
Data Index: 903512 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.6668. Min Act: -0.1700
Data Index: 1448624 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.7293. Min Act: -0.1700
Data Index: 223262 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.6668. Min Act: -0.1700
Data Index: 6856833 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.6668. Min Act: -0.1700
Data Index: 6740305 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.6668. Min Act: -0.1700
Data Index: 4973774 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.6668. Min Act: -0.1700
Data Index: 5264696 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.6043. Min Act: -0.1700
Data Index: 1664400 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.6043. Min Act: -0.1700
Data Index: 1397411 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3543. Min Range: -10.3543
Max Act: 9.5418. Min Act: -0.1700
Data Index: 1534390 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19