Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.7495. Min Act: -0.1700
Data Index: 2505602 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.7183. Min Act: -0.1700
Data Index: 6521535 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.6713. Min Act: -0.1700
Data Index: 7970264 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.6557. Min Act: -0.1700
Data Index: 5468129 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.6713. Min Act: -0.1700
Data Index: 8643033 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.6087. Min Act: -0.1700
Data Index: 3908241 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5931. Min Act: -0.1700
Data Index: 5507254 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5931. Min Act: -0.1700
Data Index: 7967884 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5618. Min Act: -0.1700
Data Index: 7477587 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5774. Min Act: -0.1700
Data Index: 7693635 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5461. Min Act: -0.1700
Data Index: 3410438 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5774. Min Act: -0.1700
Data Index: 7481776 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5461. Min Act: -0.1700
Data Index: 4068380 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5305. Min Act: -0.1700
Data Index: 7948987 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5305. Min Act: -0.1700
Data Index: 8104093 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5305. Min Act: -0.1700
Data Index: 3476350 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5305. Min Act: -0.1700
Data Index: 7128097 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5148. Min Act: -0.1700
Data Index: 5483608 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5148. Min Act: -0.1700
Data Index: 1745036 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7495. Min Range: -3.7495
Max Act: 3.5148. Min Act: -0.1700
Data Index: 3630829 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19