Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.7352. Min Act: -0.1700
Data Index: 4093694 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.7352. Min Act: -0.1700
Data Index: 271477 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.7352. Min Act: -0.1700
Data Index: 3784776 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.7040. Min Act: -0.1700
Data Index: 6575344 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.7040. Min Act: -0.1700
Data Index: 5590011 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.6727. Min Act: -0.1700
Data Index: 3006197 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.6415. Min Act: -0.1700
Data Index: 5761350 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.6415. Min Act: -0.1700
Data Index: 5207464 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5790. Min Act: -0.1700
Data Index: 195380 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5790. Min Act: -0.1700
Data Index: 6795329 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5790. Min Act: -0.1700
Data Index: 335741 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.6102. Min Act: -0.1700
Data Index: 8072528 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5477. Min Act: -0.1700
Data Index: 2317489 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5165. Min Act: -0.1700
Data Index: 195381 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5477. Min Act: -0.1700
Data Index: 1564573 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5165. Min Act: -0.1700
Data Index: 4093695 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5165. Min Act: -0.1700
Data Index: 3395913 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.5165. Min Act: -0.1700
Data Index: 5427388 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.4852. Min Act: -0.1700
Data Index: 1631681 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7352. Min Range: -4.7352
Max Act: 4.4852. Min Act: -0.1700
Data Index: 1861887 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19