Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.6031. Min Act: -0.1700
Data Index: 176880 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.2593. Min Act: -0.1700
Data Index: 4582512 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.2593. Min Act: -0.1700
Data Index: 7332924 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.2593. Min Act: -0.1700
Data Index: 7190433 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.2593. Min Act: -0.1700
Data Index: 140652 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.2593. Min Act: -0.1700
Data Index: 4488903 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.1968. Min Act: -0.1700
Data Index: 574909 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.1656. Min Act: -0.1700
Data Index: 3826418 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.1031. Min Act: -0.1700
Data Index: 1009059 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.1031. Min Act: -0.1700
Data Index: 982952 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0718. Min Act: -0.1700
Data Index: 8781537 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0406. Min Act: -0.1700
Data Index: 5077232 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0406. Min Act: -0.1700
Data Index: 2351581 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0718. Min Act: -0.1700
Data Index: 6443696 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0718. Min Act: -0.1700
Data Index: 1342970 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0093. Min Act: -0.1700
Data Index: 1852568 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0406. Min Act: -0.1700
Data Index: 597700 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0093. Min Act: -0.1700
Data Index: 272142 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0406. Min Act: -0.1700
Data Index: 6115473 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6031. Min Range: -7.6031
Max Act: 7.0093. Min Act: -0.1700
Data Index: 2892959 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19