Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 199 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1743. Min Range: -4.1743
Max Act: 4.1743. Min Act: -0.1700
Data Index: 7027776 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1743. Min Range: -4.1743
Max Act: 4.1431. Min Act: -0.1700
Data Index: 23995 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1743. Min Range: -4.1743
Max Act: 4.1743. Min Act: -0.1700
Data Index: 5305742 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1743. Min Range: -4.1743
Max Act: 4.0806. Min Act: -0.1700
Data Index: 4071789 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1743. Min Range: -4.1743
Max Act: 4.0806. Min Act: -0.1700
Data Index: 6387650 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1743. Min Range: -4.1743
Max Act: 4.0493. Min Act: -0.1700
Data Index: 5033318 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1743. Min Range: -4.1743
Max Act: 4.0493. Min Act: -0.1700
Data Index: 39736 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9868. Min Act: -0.1700
Data Index: 223138 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9868. Min Act: -0.1700
Data Index: 6808055 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9868. Min Act: -0.1700
Data Index: 4903862 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9555. Min Act: -0.1700
Data Index: 2583094 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9555. Min Act: -0.1700
Data Index: 6170020 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9243. Min Act: -0.1700
Data Index: 3452433 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9555. Min Act: -0.1700
Data Index: 622429 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9868. Min Act: -0.1700
Data Index: 4010921 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9555. Min Act: -0.1700
Data Index: 574176 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9243. Min Act: -0.1700
Data Index: 147175 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9243. Min Act: -0.1700
Data Index: 6290363 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9243. Min Act: -0.1700
Data Index: 4858805 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1743. Min Range: -4.1743
Max Act: 3.9243. Min Act: -0.1700
Data Index: 357332 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19