Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.5588. Min Act: -0.1700
Data Index: 1002894 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.5275. Min Act: -0.1700
Data Index: 3154577 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.4963. Min Act: -0.1700
Data Index: 8468696 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.4338. Min Act: -0.1700
Data Index: 8776844 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.4338. Min Act: -0.1700
Data Index: 839195 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.4025. Min Act: -0.1700
Data Index: 3678684 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.4025. Min Act: -0.1700
Data Index: 2241322 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.3400. Min Act: -0.1700
Data Index: 6628684 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.3400. Min Act: -0.1700
Data Index: 4524692 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.3400. Min Act: -0.1700
Data Index: 963205 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.3088. Min Act: -0.1700
Data Index: 4143994 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.2775. Min Act: -0.1700
Data Index: 5726359 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.3088. Min Act: -0.1700
Data Index: 5290039 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.3088. Min Act: -0.1700
Data Index: 8720200 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.2775. Min Act: -0.1700
Data Index: 3489866 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.2775. Min Act: -0.1700
Data Index: 4643638 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.2463. Min Act: -0.1700
Data Index: 7454838 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.2150. Min Act: -0.1700
Data Index: 1529122 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.2150. Min Act: -0.1700
Data Index: 5893116 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5588. Min Range: -6.5588
Max Act: 6.1838. Min Act: -0.1700
Data Index: 2381412 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19