Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1980. Min Range: -8.1980
Max Act: 8.1980. Min Act: -0.1700
Data Index: 3377206 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.6980. Min Act: -0.1700
Data Index: 4927533 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.5105. Min Act: -0.1700
Data Index: 6800626 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.4480. Min Act: -0.1700
Data Index: 5574341 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.4168. Min Act: -0.1700
Data Index: 7756967 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.3543. Min Act: -0.1700
Data Index: 2135375 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.2605. Min Act: -0.1700
Data Index: 7393073 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.2605. Min Act: -0.1700
Data Index: 2181030 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.2293. Min Act: -0.1700
Data Index: 4611724 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.1980. Min Act: -0.1700
Data Index: 6616836 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.1980. Min Act: -0.1700
Data Index: 1432839 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.1043. Min Act: -0.1700
Data Index: 6361832 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.1043. Min Act: -0.1700
Data Index: 6013464 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.0730. Min Act: -0.1700
Data Index: 3026556 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.0418. Min Act: -0.1700
Data Index: 4527405 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.0105. Min Act: -0.1700
Data Index: 758094 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1980. Min Range: -8.1980
Max Act: 7.0105. Min Act: -0.1700
Data Index: 2518933 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1980. Min Range: -8.1980
Max Act: 6.9793. Min Act: -0.1700
Data Index: 5277926 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1980. Min Range: -8.1980
Max Act: 6.9480. Min Act: -0.1700
Data Index: 8110593 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1980. Min Range: -8.1980
Max Act: 6.9480. Min Act: -0.1700
Data Index: 316313 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19