Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5063 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.3478. Min Act: -0.1700
Data Index: 6739989 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.1915. Min Act: -0.1700
Data Index: 2294808 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.1290. Min Act: -0.1700
Data Index: 3050098 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0978. Min Act: -0.1700
Data Index: 2384579 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0978. Min Act: -0.1700
Data Index: 403948 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0665. Min Act: -0.1700
Data Index: 1461218 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0665. Min Act: -0.1700
Data Index: 7018853 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0353. Min Act: -0.1700
Data Index: 828580 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0353. Min Act: -0.1700
Data Index: 2661292 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0353. Min Act: -0.1700
Data Index: 2312493 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0353. Min Act: -0.1700
Data Index: 192230 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0040. Min Act: -0.1700
Data Index: 1693210 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0040. Min Act: -0.1700
Data Index: 1261388 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0040. Min Act: -0.1700
Data Index: 8419180 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3478. Min Range: -6.3478
Max Act: 6.0040. Min Act: -0.1700
Data Index: 6398470 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3478. Min Range: -6.3478
Max Act: 5.9728. Min Act: -0.1700
Data Index: 2951688 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3478. Min Range: -6.3478
Max Act: 5.9728. Min Act: -0.1700
Data Index: 4523607 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3478. Min Range: -6.3478
Max Act: 5.9103. Min Act: -0.1700
Data Index: 2902871 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3478. Min Range: -6.3478
Max Act: 5.9415. Min Act: -0.1700
Data Index: 282552 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3478. Min Range: -6.3478
Max Act: 5.9415. Min Act: -0.1700
Data Index: 4072106 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19