Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4517 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.7613. Min Act: -0.1700
Data Index: 5472859 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.5425. Min Act: -0.1700
Data Index: 3441232 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.4800. Min Act: -0.1700
Data Index: 4340730 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.4800. Min Act: -0.1700
Data Index: 1374260 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.4488. Min Act: -0.1700
Data Index: 1233657 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.3863. Min Act: -0.1700
Data Index: 7758406 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.3550. Min Act: -0.1700
Data Index: 4740024 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.3550. Min Act: -0.1700
Data Index: 5582269 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.2613. Min Act: -0.1700
Data Index: 2647051 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.2300. Min Act: -0.1700
Data Index: 5245928 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1988. Min Act: -0.1700
Data Index: 4724402 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1988. Min Act: -0.1700
Data Index: 1222083 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1363. Min Act: -0.1700
Data Index: 624841 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1675. Min Act: -0.1700
Data Index: 8220223 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1363. Min Act: -0.1700
Data Index: 3111965 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1363. Min Act: -0.1700
Data Index: 1339970 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1675. Min Act: -0.1700
Data Index: 8049722 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1363. Min Act: -0.1700
Data Index: 3540679 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1363. Min Act: -0.1700
Data Index: 1471113 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7613. Min Range: -6.7613
Max Act: 6.1050. Min Act: -0.1700
Data Index: 649177 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19