Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 684 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1795. Min Range: -7.1795
Max Act: 7.1795. Min Act: -0.1700
Data Index: 4294018 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1795. Min Range: -7.1795
Max Act: 7.0232. Min Act: -0.1700
Data Index: 47336 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1795. Min Range: -7.1795
Max Act: 7.0232. Min Act: -0.1700
Data Index: 1901051 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.9920. Min Act: -0.1700
Data Index: 8804119 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.9295. Min Act: -0.1700
Data Index: 6830804 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.9607. Min Act: -0.1700
Data Index: 6690426 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.8357. Min Act: -0.1700
Data Index: 5085699 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.8357. Min Act: -0.1700
Data Index: 5680131 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.8045. Min Act: -0.1700
Data Index: 427501 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.8045. Min Act: -0.1700
Data Index: 3392856 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.8045. Min Act: -0.1700
Data Index: 3684647 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.7732. Min Act: -0.1700
Data Index: 5940957 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.7732. Min Act: -0.1700
Data Index: 5156967 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.7107. Min Act: -0.1700
Data Index: 3382144 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.7420. Min Act: -0.1700
Data Index: 8171927 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.7420. Min Act: -0.1700
Data Index: 7844185 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.6795. Min Act: -0.1700
Data Index: 6881317 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.7420. Min Act: -0.1700
Data Index: 2818604 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.6795. Min Act: -0.1700
Data Index: 121090 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1795. Min Range: -7.1795
Max Act: 6.6482. Min Act: -0.1700
Data Index: 2608275 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19