Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1021 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.7442. Min Act: -0.1700
Data Index: 8826247 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.7442. Min Act: -0.1700
Data Index: 8014241 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.6505. Min Act: -0.1700
Data Index: 540190 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4630. Min Act: -0.1700
Data Index: 290648 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.5567. Min Act: -0.1700
Data Index: 5747666 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4630. Min Act: -0.1700
Data Index: 4653741 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4317. Min Act: -0.1700
Data Index: 1166301 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4317. Min Act: -0.1700
Data Index: 2308287 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4630. Min Act: -0.1700
Data Index: 7109754 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4630. Min Act: -0.1700
Data Index: 1550864 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4317. Min Act: -0.1700
Data Index: 5915996 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4005. Min Act: -0.1700
Data Index: 7212700 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4005. Min Act: -0.1700
Data Index: 8129985 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4005. Min Act: -0.1700
Data Index: 1936604 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.4317. Min Act: -0.1700
Data Index: 6924837 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.3692. Min Act: -0.1700
Data Index: 6882321 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.3067. Min Act: -0.1700
Data Index: 7689256 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.3380. Min Act: -0.1700
Data Index: 4369063 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.3067. Min Act: -0.1700
Data Index: 7901707 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7442. Min Range: -4.7442
Max Act: 4.2755. Min Act: -0.1700
Data Index: 658248 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19