Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2481 in Layer 0
Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')
Click the toggle to see the full text!
Text #0
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.8506. Min Act: -0.1700
Data Index: 6321031 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7949. Min Act: -0.1700
Data Index: 469739 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7877. Min Act: -0.1700
Data Index: 5987563 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7872. Min Act: -0.1700
Data Index: 4258839 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7841. Min Act: -0.1700
Data Index: 3299999 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7540. Min Act: -0.1700
Data Index: 7422633 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7442. Min Act: -0.1700
Data Index: 8206038 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7134. Min Act: -0.1700
Data Index: 4286778 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7278. Min Act: -0.1700
Data Index: 507729 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.6765. Min Act: -0.1700
Data Index: 4285541 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.6765. Min Act: -0.1700
Data Index: 2740040 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.6811. Min Act: -0.1700
Data Index: 4032503 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7089. Min Act: -0.1700
Data Index: 6781482 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.6842. Min Act: -0.1700
Data Index: 3411014 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7055. Min Act: -0.1700
Data Index: 2207282 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.6856. Min Act: -0.1700
Data Index: 4698995 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.7065. Min Act: -0.1700
Data Index: 7145862 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.6765. Min Act: -0.1700
Data Index: 7236835 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.6765. Min Act: -0.1700
Data Index: 5638866 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 4.8506. Min Range: -4.8506
Max Act: 4.6898. Min Act: -0.1700
Data Index: 4731068 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full textTruncated
Full Text #19