Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2473 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5749. Min Act: -0.1700
Data Index: 3888656 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5124. Min Act: -0.1700
Data Index: 652317 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.5124. Min Act: -0.1700
Data Index: 1131774 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.4499. Min Act: -0.1700
Data Index: 8723597 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3874. Min Act: -0.1700
Data Index: 5024120 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3562. Min Act: -0.1700
Data Index: 2785570 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.3562. Min Act: -0.1700
Data Index: 653951 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2937. Min Act: -0.1700
Data Index: 8639670 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2937. Min Act: -0.1700
Data Index: 8519456 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2624. Min Act: -0.1700
Data Index: 6828605 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2624. Min Act: -0.1700
Data Index: 4733069 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2624. Min Act: -0.1700
Data Index: 3291611 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2312. Min Act: -0.1700
Data Index: 4800195 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2312. Min Act: -0.1700
Data Index: 1942945 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.2312. Min Act: -0.1700
Data Index: 7913063 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1999. Min Act: -0.1700
Data Index: 7925408 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1999. Min Act: -0.1700
Data Index: 7346625 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1999. Min Act: -0.1700
Data Index: 6835720 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1687. Min Act: -0.1700
Data Index: 5589013 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5749. Min Range: -5.5749
Max Act: 5.1687. Min Act: -0.1700
Data Index: 4592810 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19