Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.9363. Min Act: -0.1700
Data Index: 7304311 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.4363. Min Act: -0.1700
Data Index: 91431 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.3113. Min Act: -0.1700
Data Index: 424316 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.2488. Min Act: -0.1700
Data Index: 3938215 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.2488. Min Act: -0.1700
Data Index: 5791944 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.2488. Min Act: -0.1700
Data Index: 8429320 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.1863. Min Act: -0.1700
Data Index: 4796170 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.1863. Min Act: -0.1700
Data Index: 3730372 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.1863. Min Act: -0.1700
Data Index: 8809096 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.1238. Min Act: -0.1700
Data Index: 2464005 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.1238. Min Act: -0.1700
Data Index: 3446678 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.1238. Min Act: -0.1700
Data Index: 1199190 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.0613. Min Act: -0.1700
Data Index: 1125574 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.0613. Min Act: -0.1700
Data Index: 4410347 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9363. Min Range: -8.9363
Max Act: 8.0613. Min Act: -0.1700
Data Index: 4455677 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9363. Min Range: -8.9363
Max Act: 7.9988. Min Act: -0.1700
Data Index: 349374 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9363. Min Range: -8.9363
Max Act: 7.9988. Min Act: -0.1700
Data Index: 4519727 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9363. Min Range: -8.9363
Max Act: 7.9988. Min Act: -0.1700
Data Index: 1351419 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9363. Min Range: -8.9363
Max Act: 7.8738. Min Act: -0.1700
Data Index: 8735815 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9363. Min Range: -8.9363
Max Act: 7.9988. Min Act: -0.1700
Data Index: 2929837 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19