Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1498 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.8445. Min Act: -0.1700
Data Index: 2001997 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.8133. Min Act: -0.1700
Data Index: 4128573 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.6883. Min Act: -0.1700
Data Index: 5607852 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.5945. Min Act: -0.1700
Data Index: 1281475 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.6258. Min Act: -0.1700
Data Index: 573619 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.5320. Min Act: -0.1700
Data Index: 1994387 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.5008. Min Act: -0.1700
Data Index: 6107769 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4382. Min Act: -0.1700
Data Index: 2778081 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4695. Min Act: -0.1700
Data Index: 6004667 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4382. Min Act: -0.1700
Data Index: 4103285 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4695. Min Act: -0.1700
Data Index: 2150567 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4382. Min Act: -0.1700
Data Index: 8555127 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4070. Min Act: -0.1700
Data Index: 7509282 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4070. Min Act: -0.1700
Data Index: 7141368 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4070. Min Act: -0.1700
Data Index: 8588346 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4070. Min Act: -0.1700
Data Index: 5849567 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.4070. Min Act: -0.1700
Data Index: 1553615 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.3445. Min Act: -0.1700
Data Index: 4467925 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.3757. Min Act: -0.1700
Data Index: 6316593 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8445. Min Range: -4.8445
Max Act: 4.3445. Min Act: -0.1700
Data Index: 3255536 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19