Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 822 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.7198. Min Act: -0.1700
Data Index: 4283818 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.6558. Min Act: -0.1700
Data Index: 3211767 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.5592. Min Act: -0.1700
Data Index: 7803451 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.5107. Min Act: -0.1700
Data Index: 2187160 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.4945. Min Act: -0.1700
Data Index: 4077542 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.4458. Min Act: -0.1700
Data Index: 2218012 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.4783. Min Act: -0.1700
Data Index: 2070035 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.4621. Min Act: -0.1700
Data Index: 7935633 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.4133. Min Act: -0.1700
Data Index: 2989161 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.4458. Min Act: -0.1700
Data Index: 8562311 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.4458. Min Act: -0.1700
Data Index: 5381324 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.3643. Min Act: -0.1700
Data Index: 1582810 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.4296. Min Act: -0.1700
Data Index: 6483861 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.3970. Min Act: -0.1700
Data Index: 4936244 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.3643. Min Act: -0.1700
Data Index: 2578793 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.3806. Min Act: -0.1700
Data Index: 4950065 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.3397. Min Act: -0.1700
Data Index: 4712987 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.3970. Min Act: -0.1700
Data Index: 3578772 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.3970. Min Act: -0.1700
Data Index: 4351165 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7198. Min Range: -2.7198
Max Act: 2.3479. Min Act: -0.1700
Data Index: 6662489 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19