Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2300. Min Range: -6.2300
Max Act: 6.2300. Min Act: -0.1700
Data Index: 2984646 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.9487. Min Act: -0.1700
Data Index: 173495 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8862. Min Act: -0.1700
Data Index: 2459811 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8862. Min Act: -0.1700
Data Index: 338729 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8862. Min Act: -0.1700
Data Index: 4573465 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8862. Min Act: -0.1700
Data Index: 2313808 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8550. Min Act: -0.1700
Data Index: 4902188 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8237. Min Act: -0.1700
Data Index: 1920101 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8550. Min Act: -0.1700
Data Index: 2339404 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8237. Min Act: -0.1700
Data Index: 131818 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7925. Min Act: -0.1700
Data Index: 8367170 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7925. Min Act: -0.1700
Data Index: 2172092 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7612. Min Act: -0.1700
Data Index: 7379115 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7612. Min Act: -0.1700
Data Index: 5844753 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7300. Min Act: -0.1700
Data Index: 3769769 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7300. Min Act: -0.1700
Data Index: 7520923 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7300. Min Act: -0.1700
Data Index: 5165465 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7612. Min Act: -0.1700
Data Index: 1511086 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7300. Min Act: -0.1700
Data Index: 40682 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7300. Min Act: -0.1700
Data Index: 4448527 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19