Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 150 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.8761. Min Act: -0.1700
Data Index: 8534278 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.7511. Min Act: -0.1700
Data Index: 371495 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.7199. Min Act: -0.1700
Data Index: 8534279 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.6574. Min Act: -0.1700
Data Index: 1471998 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5949. Min Act: -0.1700
Data Index: 8220357 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5636. Min Act: -0.1700
Data Index: 7921167 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5949. Min Act: -0.1700
Data Index: 2343803 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5636. Min Act: -0.1700
Data Index: 8749228 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5324. Min Act: -0.1700
Data Index: 8534273 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5324. Min Act: -0.1700
Data Index: 2274326 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5324. Min Act: -0.1700
Data Index: 8394733 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5011. Min Act: -0.1700
Data Index: 3311535 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4699. Min Act: -0.1700
Data Index: 8534280 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4699. Min Act: -0.1700
Data Index: 8058321 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4386. Min Act: -0.1700
Data Index: 6117249 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4074. Min Act: -0.1700
Data Index: 2460051 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4074. Min Act: -0.1700
Data Index: 8534281 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4386. Min Act: -0.1700
Data Index: 8058324 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4074. Min Act: -0.1700
Data Index: 6512059 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.3449. Min Act: -0.1700
Data Index: 7076456 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19