Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3616 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.6812. Min Act: -0.1700
Data Index: 1200266 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.6500. Min Act: -0.1700
Data Index: 8661081 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.4937. Min Act: -0.1700
Data Index: 6283709 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.5562. Min Act: -0.1700
Data Index: 1357521 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.4625. Min Act: -0.1700
Data Index: 3308906 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.4625. Min Act: -0.1700
Data Index: 5522329 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.4625. Min Act: -0.1700
Data Index: 212594 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3687. Min Act: -0.1700
Data Index: 5448222 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.4312. Min Act: -0.1700
Data Index: 3463361 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.4000. Min Act: -0.1700
Data Index: 1514677 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.4000. Min Act: -0.1700
Data Index: 2144921 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3687. Min Act: -0.1700
Data Index: 8162638 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3687. Min Act: -0.1700
Data Index: 8649297 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3062. Min Act: -0.1700
Data Index: 7659760 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3375. Min Act: -0.1700
Data Index: 3694749 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3375. Min Act: -0.1700
Data Index: 8479600 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3375. Min Act: -0.1700
Data Index: 2229131 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3375. Min Act: -0.1700
Data Index: 4634077 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3375. Min Act: -0.1700
Data Index: 8095385 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6812. Min Range: -5.6812
Max Act: 5.3062. Min Act: -0.1700
Data Index: 6403135 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19