Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2385 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3425. Min Range: -8.3425
Max Act: 8.3425. Min Act: -0.1700
Data Index: 3449351 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.9050. Min Act: -0.1700
Data Index: 8777680 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.8425. Min Act: -0.1700
Data Index: 5746933 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.7175. Min Act: -0.1700
Data Index: 467992 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.6863. Min Act: -0.1700
Data Index: 5124259 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.6238. Min Act: -0.1700
Data Index: 2576213 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.5925. Min Act: -0.1700
Data Index: 8200525 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.5300. Min Act: -0.1700
Data Index: 8528529 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.5300. Min Act: -0.1700
Data Index: 1872002 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.4988. Min Act: -0.1700
Data Index: 721909 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.4988. Min Act: -0.1700
Data Index: 5535465 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.4363. Min Act: -0.1700
Data Index: 3146849 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.4050. Min Act: -0.1700
Data Index: 3261874 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.4363. Min Act: -0.1700
Data Index: 4275214 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.4363. Min Act: -0.1700
Data Index: 7057045 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.4363. Min Act: -0.1700
Data Index: 965060 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.4050. Min Act: -0.1700
Data Index: 6680094 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.4050. Min Act: -0.1700
Data Index: 881123 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.3738. Min Act: -0.1700
Data Index: 6674783 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3425. Min Range: -8.3425
Max Act: 7.3425. Min Act: -0.1700
Data Index: 2103956 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19