Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.9185. Min Act: -0.1700
Data Index: 1613050 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.8872. Min Act: -0.1700
Data Index: 5907672 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.7310. Min Act: -0.1700
Data Index: 6662852 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.7622. Min Act: -0.1700
Data Index: 977897 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.7310. Min Act: -0.1700
Data Index: 1468859 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6997. Min Act: -0.1700
Data Index: 7471536 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6685. Min Act: -0.1700
Data Index: 6987381 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6372. Min Act: -0.1700
Data Index: 102159 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6372. Min Act: -0.1700
Data Index: 3955522 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6060. Min Act: -0.1700
Data Index: 5497267 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6372. Min Act: -0.1700
Data Index: 2125911 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6060. Min Act: -0.1700
Data Index: 189898 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6060. Min Act: -0.1700
Data Index: 8512092 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.5747. Min Act: -0.1700
Data Index: 3211097 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6060. Min Act: -0.1700
Data Index: 4566158 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.6060. Min Act: -0.1700
Data Index: 8672572 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.5747. Min Act: -0.1700
Data Index: 3517583 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.5747. Min Act: -0.1700
Data Index: 3987333 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.5747. Min Act: -0.1700
Data Index: 3602346 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9185. Min Range: -5.9185
Max Act: 5.5435. Min Act: -0.1700
Data Index: 6200822 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19