Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 798 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.6905. Min Act: -0.1700
Data Index: 7699390 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.7061. Min Act: -0.1700
Data Index: 3477372 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.6748. Min Act: -0.1700
Data Index: 74632 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.6748. Min Act: -0.1700
Data Index: 8792375 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.6592. Min Act: -0.1700
Data Index: 7775036 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5966. Min Act: -0.1700
Data Index: 3257399 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5653. Min Act: -0.1700
Data Index: 3985590 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5653. Min Act: -0.1700
Data Index: 4373880 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5183. Min Act: -0.1700
Data Index: 1195201 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5496. Min Act: -0.1700
Data Index: 8813300 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5183. Min Act: -0.1700
Data Index: 784361 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5496. Min Act: -0.1700
Data Index: 7232503 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5340. Min Act: -0.1700
Data Index: 1400851 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5340. Min Act: -0.1700
Data Index: 5494044 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5183. Min Act: -0.1700
Data Index: 1924164 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5496. Min Act: -0.1700
Data Index: 4328400 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5027. Min Act: -0.1700
Data Index: 3539703 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5496. Min Act: -0.1700
Data Index: 6617202 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5183. Min Act: -0.1700
Data Index: 3141421 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7061. Min Range: -3.7061
Max Act: 3.5183. Min Act: -0.1700
Data Index: 2166010 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19