Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 90 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.2796. Min Act: -0.1700
Data Index: 600334 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.2484. Min Act: -0.1700
Data Index: 2290754 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.1546. Min Act: -0.1700
Data Index: 4942627 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.1234. Min Act: -0.1700
Data Index: 3980271 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.1234. Min Act: -0.1700
Data Index: 5558983 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.1234. Min Act: -0.1700
Data Index: 7173651 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.1234. Min Act: -0.1700
Data Index: 5023590 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.0921. Min Act: -0.1700
Data Index: 999014 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.0296. Min Act: -0.1700
Data Index: 1564980 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.0609. Min Act: -0.1700
Data Index: 4198572 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.0296. Min Act: -0.1700
Data Index: 1312422 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2796. Min Range: -5.2796
Max Act: 5.0296. Min Act: -0.1700
Data Index: 7143780 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2796. Min Range: -5.2796
Max Act: 4.9671. Min Act: -0.1700
Data Index: 6578489 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2796. Min Range: -5.2796
Max Act: 4.9671. Min Act: -0.1700
Data Index: 5784396 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2796. Min Range: -5.2796
Max Act: 4.9359. Min Act: -0.1700
Data Index: 2759671 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2796. Min Range: -5.2796
Max Act: 4.9359. Min Act: -0.1700
Data Index: 5601521 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2796. Min Range: -5.2796
Max Act: 4.9359. Min Act: -0.1700
Data Index: 829128 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2796. Min Range: -5.2796
Max Act: 4.9046. Min Act: -0.1700
Data Index: 3547722 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2796. Min Range: -5.2796
Max Act: 4.9359. Min Act: -0.1700
Data Index: 3259656 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2796. Min Range: -5.2796
Max Act: 4.9359. Min Act: -0.1700
Data Index: 1228106 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19