Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.3217. Min Act: -0.1700
Data Index: 7101996 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.2592. Min Act: -0.1700
Data Index: 8488968 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.2592. Min Act: -0.1700
Data Index: 2235184 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.2592. Min Act: -0.1700
Data Index: 4700755 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.1655. Min Act: -0.1700
Data Index: 6832260 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.1342. Min Act: -0.1700
Data Index: 3568133 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.1030. Min Act: -0.1700
Data Index: 8014415 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.1030. Min Act: -0.1700
Data Index: 6767011 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.0717. Min Act: -0.1700
Data Index: 5161377 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.0405. Min Act: -0.1700
Data Index: 1397504 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.0092. Min Act: -0.1700
Data Index: 424160 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.0092. Min Act: -0.1700
Data Index: 375110 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.0092. Min Act: -0.1700
Data Index: 4020238 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3217. Min Range: -5.3217
Max Act: 5.0092. Min Act: -0.1700
Data Index: 7198823 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.9780. Min Act: -0.1700
Data Index: 4154146 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.9780. Min Act: -0.1700
Data Index: 6461860 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.9780. Min Act: -0.1700
Data Index: 6279601 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.9780. Min Act: -0.1700
Data Index: 228024 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.9780. Min Act: -0.1700
Data Index: 1668142 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3217. Min Range: -5.3217
Max Act: 4.9780. Min Act: -0.1700
Data Index: 940151 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19