Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1509 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1826. Min Range: -5.1826
Max Act: 5.1826. Min Act: -0.1700
Data Index: 4664309 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1826. Min Range: -5.1826
Max Act: 5.0889. Min Act: -0.1700
Data Index: 4934869 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1826. Min Range: -5.1826
Max Act: 5.0889. Min Act: -0.1700
Data Index: 2018955 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1826. Min Range: -5.1826
Max Act: 5.0889. Min Act: -0.1700
Data Index: 569432 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1826. Min Range: -5.1826
Max Act: 5.0889. Min Act: -0.1700
Data Index: 8413973 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1826. Min Range: -5.1826
Max Act: 5.0889. Min Act: -0.1700
Data Index: 981302 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1826. Min Range: -5.1826
Max Act: 5.0264. Min Act: -0.1700
Data Index: 7476269 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9639. Min Act: -0.1700
Data Index: 4838905 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9951. Min Act: -0.1700
Data Index: 6917160 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9639. Min Act: -0.1700
Data Index: 882016 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9639. Min Act: -0.1700
Data Index: 8313042 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9639. Min Act: -0.1700
Data Index: 6234111 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9326. Min Act: -0.1700
Data Index: 7844068 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9014. Min Act: -0.1700
Data Index: 1094674 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9014. Min Act: -0.1700
Data Index: 2930248 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9014. Min Act: -0.1700
Data Index: 4436193 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.8701. Min Act: -0.1700
Data Index: 561001 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.8701. Min Act: -0.1700
Data Index: 8272329 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.8701. Min Act: -0.1700
Data Index: 3914540 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1826. Min Range: -5.1826
Max Act: 4.9014. Min Act: -0.1700
Data Index: 1774969 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19