Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.9608. Min Act: -0.1700
Data Index: 2425199 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.9608. Min Act: -0.1700
Data Index: 7518801 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.9449. Min Act: -0.1700
Data Index: 748196 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.9291. Min Act: -0.1700
Data Index: 3531282 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8974. Min Act: -0.1700
Data Index: 2174610 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.9132. Min Act: -0.1700
Data Index: 4055092 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8974. Min Act: -0.1700
Data Index: 5666520 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8974. Min Act: -0.1700
Data Index: 5525580 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8815. Min Act: -0.1700
Data Index: 1935188 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8974. Min Act: -0.1700
Data Index: 7010339 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8815. Min Act: -0.1700
Data Index: 5903468 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8815. Min Act: -0.1700
Data Index: 3098312 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8815. Min Act: -0.1700
Data Index: 9425 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8815. Min Act: -0.1700
Data Index: 3448634 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8815. Min Act: -0.1700
Data Index: 6299248 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8974. Min Act: -0.1700
Data Index: 7460584 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8657. Min Act: -0.1700
Data Index: 2945297 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8657. Min Act: -0.1700
Data Index: 3112844 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8657. Min Act: -0.1700
Data Index: 7195133 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9608. Min Range: -2.9608
Max Act: 2.8815. Min Act: -0.1700
Data Index: 7406935 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19