Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4791 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.8302. Min Act: -0.1700
Data Index: 2853620 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.8302. Min Act: -0.1700
Data Index: 1194304 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.8302. Min Act: -0.1700
Data Index: 7937963 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7989. Min Act: -0.1700
Data Index: 8815582 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7677. Min Act: -0.1700
Data Index: 8789037 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7677. Min Act: -0.1700
Data Index: 260389 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7677. Min Act: -0.1700
Data Index: 3451368 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7677. Min Act: -0.1700
Data Index: 8446785 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7677. Min Act: -0.1700
Data Index: 766839 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7677. Min Act: -0.1700
Data Index: 7386347 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7364. Min Act: -0.1700
Data Index: 2793299 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7052. Min Act: -0.1700
Data Index: 409399 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7052. Min Act: -0.1700
Data Index: 3543888 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6739. Min Act: -0.1700
Data Index: 2705876 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7052. Min Act: -0.1700
Data Index: 5528362 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6739. Min Act: -0.1700
Data Index: 4141823 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6739. Min Act: -0.1700
Data Index: 7278641 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6739. Min Act: -0.1700
Data Index: 6598980 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6739. Min Act: -0.1699
Data Index: 3665389 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6427. Min Act: -0.1700
Data Index: 3647780 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19