Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2732. Min Range: -6.2732
Max Act: 6.2732. Min Act: -0.1700
Data Index: 1287981 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2732. Min Range: -6.2732
Max Act: 6.2419. Min Act: -0.1700
Data Index: 3910344 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2732. Min Range: -6.2732
Max Act: 6.2419. Min Act: -0.1700
Data Index: 4785218 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.9294. Min Act: -0.1700
Data Index: 1604350 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8669. Min Act: -0.1700
Data Index: 3877345 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8669. Min Act: -0.1700
Data Index: 6522407 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8357. Min Act: -0.1700
Data Index: 2157539 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8044. Min Act: -0.1700
Data Index: 6922993 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7732. Min Act: -0.1700
Data Index: 7865765 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7732. Min Act: -0.1700
Data Index: 7224674 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7419. Min Act: -0.1700
Data Index: 8760919 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7419. Min Act: -0.1700
Data Index: 7474726 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7419. Min Act: -0.1700
Data Index: 3534860 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7419. Min Act: -0.1700
Data Index: 6268167 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7107. Min Act: -0.1700
Data Index: 7792999 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7419. Min Act: -0.1700
Data Index: 6993385 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7732. Min Act: -0.1700
Data Index: 5556073 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7107. Min Act: -0.1700
Data Index: 4752445 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7107. Min Act: -0.1700
Data Index: 6452079 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.7107. Min Act: -0.1700
Data Index: 5737606 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19