Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3758 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0707. Min Range: -7.0707
Max Act: 7.0707. Min Act: -0.1700
Data Index: 967451 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.8520. Min Act: -0.1700
Data Index: 3944422 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.8207. Min Act: -0.1700
Data Index: 2945976 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.7582. Min Act: -0.1700
Data Index: 7906371 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.7895. Min Act: -0.1700
Data Index: 782647 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.7895. Min Act: -0.1700
Data Index: 5427211 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.7582. Min Act: -0.1700
Data Index: 2573753 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.7582. Min Act: -0.1700
Data Index: 4848809 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.7582. Min Act: -0.1700
Data Index: 6138902 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.7270. Min Act: -0.1700
Data Index: 3766452 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.7582. Min Act: -0.1700
Data Index: 6998004 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.6957. Min Act: -0.1700
Data Index: 3284121 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.7270. Min Act: -0.1700
Data Index: 6291318 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.6645. Min Act: -0.1700
Data Index: 1058024 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.6645. Min Act: -0.1700
Data Index: 4981139 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.6645. Min Act: -0.1700
Data Index: 5619203 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.6020. Min Act: -0.1700
Data Index: 3433303 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.6332. Min Act: -0.1700
Data Index: 6587678 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.6020. Min Act: -0.1700
Data Index: 7225153 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0707. Min Range: -7.0707
Max Act: 6.5707. Min Act: -0.1700
Data Index: 2723515 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19