Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1858 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.2170. Min Act: -0.1700
Data Index: 5506065 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.1545. Min Act: -0.1700
Data Index: 8620291 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2170. Min Range: -5.2170
Max Act: 5.0920. Min Act: -0.1700
Data Index: 1878051 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.9670. Min Act: -0.1700
Data Index: 7145038 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.9357. Min Act: -0.1700
Data Index: 997867 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.9045. Min Act: -0.1700
Data Index: 6625197 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.8732. Min Act: -0.1700
Data Index: 1948149 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.8732. Min Act: -0.1700
Data Index: 3604796 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.8732. Min Act: -0.1700
Data Index: 2418404 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.8420. Min Act: -0.1700
Data Index: 4605813 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.8420. Min Act: -0.1700
Data Index: 137082 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.8107. Min Act: -0.1700
Data Index: 4514126 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.8107. Min Act: -0.1700
Data Index: 2844327 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.8107. Min Act: -0.1700
Data Index: 5892377 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7795. Min Act: -0.1700
Data Index: 314791 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7795. Min Act: -0.1700
Data Index: 3831295 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7795. Min Act: -0.1700
Data Index: 1463281 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7170. Min Act: -0.1700
Data Index: 4863685 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.7170. Min Act: -0.1700
Data Index: 154602 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2170. Min Range: -5.2170
Max Act: 4.6857. Min Act: -0.1700
Data Index: 4709751 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19