Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.7984. Min Act: -0.1700
Data Index: 7705653 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.7359. Min Act: -0.1700
Data Index: 2872602 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.6422. Min Act: -0.1700
Data Index: 6698849 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.5797. Min Act: -0.1700
Data Index: 3342573 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.3922. Min Act: -0.1700
Data Index: 5115140 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.2984. Min Act: -0.1700
Data Index: 943962 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.2984. Min Act: -0.1700
Data Index: 4816858 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.2984. Min Act: -0.1700
Data Index: 2498956 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.2359. Min Act: -0.1700
Data Index: 922528 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.2359. Min Act: -0.1700
Data Index: 3489434 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.2047. Min Act: -0.1700
Data Index: 5593015 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.1734. Min Act: -0.1700
Data Index: 376142 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.1422. Min Act: -0.1700
Data Index: 1961140 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.1422. Min Act: -0.1700
Data Index: 235548 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.1422. Min Act: -0.1700
Data Index: 804929 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.1422. Min Act: -0.1700
Data Index: 7273813 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.1109. Min Act: -0.1700
Data Index: 842535 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.1109. Min Act: -0.1700
Data Index: 2280863 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.0797. Min Act: -0.1700
Data Index: 2353285 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7984. Min Range: -7.7984
Max Act: 7.0484. Min Act: -0.1700
Data Index: 2273624 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19