Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5742 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4241. Min Range: -9.4241
Max Act: 9.4241. Min Act: -0.1700
Data Index: 3853499 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.6741. Min Act: -0.1700
Data Index: 6392416 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.6741. Min Act: -0.1700
Data Index: 4192257 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.6741. Min Act: -0.1700
Data Index: 4192258 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.6741. Min Act: -0.1700
Data Index: 7509614 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.6116. Min Act: -0.1700
Data Index: 1970716 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.6116. Min Act: -0.1700
Data Index: 3348841 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.6116. Min Act: -0.1700
Data Index: 1471225 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.6116. Min Act: -0.1700
Data Index: 6392417 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.6116. Min Act: -0.1700
Data Index: 7509613 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.4866. Min Act: -0.1700
Data Index: 1821478 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.3616. Min Act: -0.1700
Data Index: 6386364 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.3616. Min Act: -0.1700
Data Index: 6900901 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.3616. Min Act: -0.1700
Data Index: 3178289 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.3616. Min Act: -0.1700
Data Index: 2083313 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.2991. Min Act: -0.1700
Data Index: 8370276 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.2366. Min Act: -0.1700
Data Index: 3686322 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.2366. Min Act: -0.1700
Data Index: 3198259 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.2366. Min Act: -0.1700
Data Index: 2718399 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4241. Min Range: -9.4241
Max Act: 8.1741. Min Act: -0.1700
Data Index: 5948416 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19