Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5282. Min Range: -6.5282
Max Act: 6.5282. Min Act: -0.1700
Data Index: 5380475 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5282. Min Range: -6.5282
Max Act: 6.1532. Min Act: -0.1699
Data Index: 2640443 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5282. Min Range: -6.5282
Max Act: 6.1220. Min Act: -0.1700
Data Index: 501518 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.9657. Min Act: -0.1700
Data Index: 1541879 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.9345. Min Act: -0.1700
Data Index: 7870594 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.9032. Min Act: -0.1700
Data Index: 519917 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.8407. Min Act: -0.1700
Data Index: 6052948 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.8095. Min Act: -0.1699
Data Index: 2453532 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.8407. Min Act: -0.1697
Data Index: 6619571 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.8407. Min Act: -0.1700
Data Index: 5599869 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.8095. Min Act: -0.1700
Data Index: 4580892 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.7782. Min Act: -0.1700
Data Index: 7503126 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.7782. Min Act: -0.1700
Data Index: 8804046 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.8095. Min Act: -0.1700
Data Index: 4178857 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.7470. Min Act: -0.1700
Data Index: 4138457 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.7157. Min Act: -0.1700
Data Index: 2728240 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.7157. Min Act: -0.1700
Data Index: 723806 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.7157. Min Act: -0.1700
Data Index: 8507121 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.6845. Min Act: -0.1700
Data Index: 6008739 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5282. Min Range: -6.5282
Max Act: 5.6845. Min Act: -0.1700
Data Index: 7758152 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19