Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1622 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.9761. Min Act: -0.1700
Data Index: 7428343 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.8810. Min Act: -0.1700
Data Index: 6878001 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.8943. Min Act: -0.1700
Data Index: 3432220 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.8933. Min Act: -0.1700
Data Index: 6261663 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.8635. Min Act: -0.1700
Data Index: 1184211 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.8448. Min Act: -0.1700
Data Index: 4179263 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.8365. Min Act: -0.1700
Data Index: 4769350 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.8280. Min Act: -0.1700
Data Index: 5840112 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7982. Min Act: -0.1700
Data Index: 2588431 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7953. Min Act: -0.1700
Data Index: 807476 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.8025. Min Act: -0.1700
Data Index: 6354231 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.8063. Min Act: -0.1700
Data Index: 4795078 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7889. Min Act: -0.1700
Data Index: 2425046 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7989. Min Act: -0.1700
Data Index: 610150 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7537. Min Act: -0.1700
Data Index: 3445868 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7626. Min Act: -0.1700
Data Index: 5508646 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7452. Min Act: -0.1700
Data Index: 1672939 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7221. Min Act: -0.1700
Data Index: 1508627 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7455. Min Act: -0.1700
Data Index: 540427 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.9761. Min Range: -3.9761
Max Act: 3.7217. Min Act: -0.1700
Data Index: 434476 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full textTruncated
Full Text #19