Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.5262. Min Act: -0.1700
Data Index: 3402925 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.5575. Min Act: -0.1700
Data Index: 1823743 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4950. Min Act: -0.1700
Data Index: 7486850 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4950. Min Act: -0.1700
Data Index: 2991013 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4637. Min Act: -0.1700
Data Index: 7271723 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4325. Min Act: -0.1700
Data Index: 4606846 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4325. Min Act: -0.1700
Data Index: 5927536 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4325. Min Act: -0.1700
Data Index: 6930174 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4012. Min Act: -0.1700
Data Index: 5305189 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4012. Min Act: -0.1700
Data Index: 4904334 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4012. Min Act: -0.1700
Data Index: 8283219 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3700. Min Act: -0.1700
Data Index: 223853 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.4012. Min Act: -0.1700
Data Index: 5614870 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3700. Min Act: -0.1700
Data Index: 4484667 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3387. Min Act: -0.1700
Data Index: 4887859 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3700. Min Act: -0.1700
Data Index: 7857717 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3700. Min Act: -0.1700
Data Index: 2152872 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3700. Min Act: -0.1700
Data Index: 6010781 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3387. Min Act: -0.1700
Data Index: 6623935 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5575. Min Range: -5.5575
Max Act: 5.3075. Min Act: -0.1700
Data Index: 1495071 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19