Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 3
Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')
Click the toggle to see the full text!
Text #0
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.7429. Min Act: -0.1700
Data Index: 1003857 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6994. Min Act: -0.1700
Data Index: 2407966 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6802. Min Act: -0.1700
Data Index: 5446764 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6821. Min Act: -0.1700
Data Index: 5761889 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6572. Min Act: -0.1700
Data Index: 3210154 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6679. Min Act: -0.1700
Data Index: 5923748 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6231. Min Act: -0.1700
Data Index: 6990485 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6180. Min Act: -0.1700
Data Index: 8458161 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6294. Min Act: -0.1700
Data Index: 8272275 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6278. Min Act: -0.1700
Data Index: 8098203 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6573. Min Act: -0.1700
Data Index: 3346385 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.5915. Min Act: -0.1700
Data Index: 8071135 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.5990. Min Act: -0.1700
Data Index: 5504677 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6019. Min Act: -0.1700
Data Index: 7708021 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.5972. Min Act: -0.1700
Data Index: 6419935 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6059. Min Act: -0.1700
Data Index: 2569339 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6081. Min Act: -0.1700
Data Index: 4212646 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.6082. Min Act: -0.1700
Data Index: 6845950 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.5837. Min Act: -0.1700
Data Index: 6997663 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.7429. Min Range: -3.7429
Max Act: 3.5801. Min Act: -0.1700
Data Index: 5825646 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full textTruncated
Full Text #19