Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3883 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.7386. Min Act: -0.1700
Data Index: 139500 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.6761. Min Act: -0.1700
Data Index: 7658619 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.6449. Min Act: -0.1700
Data Index: 2710854 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.5824. Min Act: -0.1700
Data Index: 5029487 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.5511. Min Act: -0.1700
Data Index: 4297053 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.3949. Min Act: -0.1700
Data Index: 3716755 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.3011. Min Act: -0.1700
Data Index: 619180 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.2699. Min Act: -0.1700
Data Index: 8258614 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.2386. Min Act: -0.1700
Data Index: 581168 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.2074. Min Act: -0.1700
Data Index: 7057942 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.0824. Min Act: -0.1700
Data Index: 65478 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.1136. Min Act: -0.1700
Data Index: 5735297 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.0199. Min Act: -0.1700
Data Index: 1425598 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.0199. Min Act: -0.1700
Data Index: 3924749 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.0199. Min Act: -0.1700
Data Index: 4564760 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7386. Min Range: -7.7386
Max Act: 6.9886. Min Act: -0.1700
Data Index: 8189084 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7386. Min Range: -7.7386
Max Act: 6.9886. Min Act: -0.1700
Data Index: 7787344 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7386. Min Range: -7.7386
Max Act: 6.9261. Min Act: -0.1700
Data Index: 4650347 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7386. Min Range: -7.7386
Max Act: 6.9574. Min Act: -0.1700
Data Index: 6900919 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7386. Min Range: -7.7386
Max Act: 6.8949. Min Act: -0.1700
Data Index: 4313949 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19