Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1805 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.9756. Min Act: -0.1700
Data Index: 5009717 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.7881. Min Act: -0.1700
Data Index: 663706 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.6631. Min Act: -0.1700
Data Index: 3605873 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.6006. Min Act: -0.1700
Data Index: 1550312 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.5381. Min Act: -0.1700
Data Index: 3968301 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.5381. Min Act: -0.1700
Data Index: 4957911 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.5381. Min Act: -0.1700
Data Index: 3807223 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 8585794 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 2019972 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 6164570 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 1082648 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 5921201 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 8629862 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.5381. Min Act: -0.1700
Data Index: 49527 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 4686949 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 8342436 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4131. Min Act: -0.1700
Data Index: 7878017 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4131. Min Act: -0.1700
Data Index: 7800654 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.3506. Min Act: -0.1700
Data Index: 1848826 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9756. Min Range: -8.9756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 3541901 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19