Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4926 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.6184. Min Act: -0.1700
Data Index: 3918475 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.3996. Min Act: -0.1700
Data Index: 5447594 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.3684. Min Act: -0.1700
Data Index: 5834348 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.2746. Min Act: -0.1700
Data Index: 1058993 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.2746. Min Act: -0.1700
Data Index: 3491743 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.2746. Min Act: -0.1700
Data Index: 4771280 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.2434. Min Act: -0.1700
Data Index: 6330419 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.2121. Min Act: -0.1700
Data Index: 921444 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.2434. Min Act: -0.1700
Data Index: 6208641 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.1808. Min Act: -0.1700
Data Index: 6660867 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.1496. Min Act: -0.1700
Data Index: 6756782 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.1183. Min Act: -0.1700
Data Index: 3241585 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.1496. Min Act: -0.1700
Data Index: 2344253 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.1183. Min Act: -0.1700
Data Index: 6763375 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.1183. Min Act: -0.1700
Data Index: 8145274 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.1183. Min Act: -0.1700
Data Index: 8720340 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.0871. Min Act: -0.1700
Data Index: 4254498 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.0871. Min Act: -0.1700
Data Index: 5583563 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.0871. Min Act: -0.1700
Data Index: 608147 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6184. Min Range: -4.6184
Max Act: 4.1183. Min Act: -0.1700
Data Index: 1076556 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19