Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.8839. Min Act: -0.1700
Data Index: 889446 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.8527. Min Act: -0.1700
Data Index: 7464917 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.7902. Min Act: -0.1700
Data Index: 3372541 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.7902. Min Act: -0.1700
Data Index: 4725169 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.7589. Min Act: -0.1700
Data Index: 6945260 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.7589. Min Act: -0.1700
Data Index: 3275232 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.7277. Min Act: -0.1700
Data Index: 1514472 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.6652. Min Act: -0.1700
Data Index: 5347978 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.6339. Min Act: -0.1700
Data Index: 7306347 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.6652. Min Act: -0.1700
Data Index: 993713 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.6339. Min Act: -0.1700
Data Index: 6273386 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.6339. Min Act: -0.1700
Data Index: 1403409 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.6339. Min Act: -0.1700
Data Index: 4762270 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.6339. Min Act: -0.1700
Data Index: 8257652 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.6027. Min Act: -0.1700
Data Index: 7365182 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.5402. Min Act: -0.1700
Data Index: 708987 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.5714. Min Act: -0.1700
Data Index: 6451994 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.5714. Min Act: -0.1700
Data Index: 4185353 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.5714. Min Act: -0.1700
Data Index: 4533840 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8839. Min Range: -5.8839
Max Act: 5.5714. Min Act: -0.1700
Data Index: 512393 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19