Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.4673. Min Act: -0.1700
Data Index: 8530310 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.3110. Min Act: -0.1700
Data Index: 5622703 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.1860. Min Act: -0.1700
Data Index: 3213578 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.2172. Min Act: -0.1700
Data Index: 4032497 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.1547. Min Act: -0.1700
Data Index: 3185878 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.0922. Min Act: -0.1700
Data Index: 368618 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.0610. Min Act: -0.1700
Data Index: 2282730 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.0610. Min Act: -0.1700
Data Index: 7149383 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.0297. Min Act: -0.1700
Data Index: 6052515 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.0297. Min Act: -0.1700
Data Index: 368619 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4673. Min Range: -4.4673
Max Act: 4.0297. Min Act: -0.1700
Data Index: 162626 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4673. Min Range: -4.4673
Max Act: 3.9984. Min Act: -0.1700
Data Index: 2792597 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4673. Min Range: -4.4673
Max Act: 3.9359. Min Act: -0.1700
Data Index: 8062818 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4673. Min Range: -4.4673
Max Act: 3.9672. Min Act: -0.1700
Data Index: 823518 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4673. Min Range: -4.4673
Max Act: 3.9359. Min Act: -0.1700
Data Index: 2879547 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4673. Min Range: -4.4673
Max Act: 3.9359. Min Act: -0.1700
Data Index: 1877534 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4673. Min Range: -4.4673
Max Act: 3.9672. Min Act: -0.1700
Data Index: 738407 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4673. Min Range: -4.4673
Max Act: 3.9047. Min Act: -0.1700
Data Index: 1041888 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4673. Min Range: -4.4673
Max Act: 3.8734. Min Act: -0.1700
Data Index: 5658698 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4673. Min Range: -4.4673
Max Act: 3.9047. Min Act: -0.1700
Data Index: 5292107 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19