Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.2689. Min Act: -0.1700
Data Index: 8146123 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.2377. Min Act: -0.1700
Data Index: 4999838 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.2377. Min Act: -0.1700
Data Index: 4999834 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.2064. Min Act: -0.1700
Data Index: 2263760 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.2064. Min Act: -0.1700
Data Index: 7787814 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.2064. Min Act: -0.1700
Data Index: 5073122 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.1752. Min Act: -0.1700
Data Index: 4156171 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.2064. Min Act: -0.1700
Data Index: 3491054 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.1752. Min Act: -0.1700
Data Index: 6375641 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.1439. Min Act: -0.1700
Data Index: 1790917 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.1127. Min Act: -0.1700
Data Index: 8377934 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.1127. Min Act: -0.1700
Data Index: 4521709 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.1127. Min Act: -0.1700
Data Index: 146948 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.0814. Min Act: -0.1700
Data Index: 2535653 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.1127. Min Act: -0.1700
Data Index: 8208753 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.0814. Min Act: -0.1700
Data Index: 612751 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.0814. Min Act: -0.1700
Data Index: 6262989 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.0814. Min Act: -0.1700
Data Index: 953374 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.0502. Min Act: -0.1700
Data Index: 2150792 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2689. Min Range: -5.2689
Max Act: 5.0189. Min Act: -0.1700
Data Index: 7468464 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19