Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.7106. Min Act: -0.1700
Data Index: 5362537 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.5541. Min Act: -0.1700
Data Index: 1245997 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.5541. Min Act: -0.1700
Data Index: 1430173 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.5071. Min Act: -0.1700
Data Index: 5127691 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.4914. Min Act: -0.1700
Data Index: 4628103 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.5071. Min Act: -0.1700
Data Index: 5700856 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.5071. Min Act: -0.1700
Data Index: 2561291 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.5071. Min Act: -0.1700
Data Index: 7823237 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.4601. Min Act: -0.1700
Data Index: 8030114 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.4601. Min Act: -0.1700
Data Index: 7152953 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.4444. Min Act: -0.1700
Data Index: 2616590 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.4601. Min Act: -0.1700
Data Index: 782410 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.4288. Min Act: -0.1700
Data Index: 5430968 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.4131. Min Act: -0.1700
Data Index: 5358749 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.3974. Min Act: -0.1700
Data Index: 4822242 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.3817. Min Act: -0.1700
Data Index: 1868898 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.3660. Min Act: -0.1700
Data Index: 3372938 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.3190. Min Act: -0.1700
Data Index: 6550620 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.3660. Min Act: -0.1700
Data Index: 6273203 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7106. Min Range: -3.7106
Max Act: 3.3347. Min Act: -0.1700
Data Index: 5791938 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19