Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4169 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3699. Min Range: -5.3699
Max Act: 5.3699. Min Act: -0.1700
Data Index: 2894553 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3699. Min Range: -5.3699
Max Act: 5.0886. Min Act: -0.1700
Data Index: 5717402 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3699. Min Range: -5.3699
Max Act: 5.0574. Min Act: -0.1700
Data Index: 4524459 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3699. Min Range: -5.3699
Max Act: 5.0574. Min Act: -0.1700
Data Index: 7075057 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3699. Min Range: -5.3699
Max Act: 5.0261. Min Act: -0.1700
Data Index: 6392491 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3699. Min Range: -5.3699
Max Act: 5.0261. Min Act: -0.1700
Data Index: 7405010 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3699. Min Range: -5.3699
Max Act: 5.0261. Min Act: -0.1700
Data Index: 5733399 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9949. Min Act: -0.1700
Data Index: 5955372 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9949. Min Act: -0.1700
Data Index: 6522958 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9636. Min Act: -0.1700
Data Index: 461784 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9636. Min Act: -0.1700
Data Index: 7075056 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9636. Min Act: -0.1700
Data Index: 7075055 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9636. Min Act: -0.1700
Data Index: 1398753 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9636. Min Act: -0.1700
Data Index: 7501461 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9636. Min Act: -0.1700
Data Index: 2355127 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9324. Min Act: -0.1700
Data Index: 5137278 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9324. Min Act: -0.1700
Data Index: 1464737 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9324. Min Act: -0.1700
Data Index: 3974183 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9324. Min Act: -0.1700
Data Index: 5092708 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3699. Min Range: -5.3699
Max Act: 4.9636. Min Act: -0.1700
Data Index: 4798577 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19