Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.7858. Min Act: -0.1700
Data Index: 5571591 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.6920. Min Act: -0.1700
Data Index: 7305284 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.6295. Min Act: -0.1700
Data Index: 7635819 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.6295. Min Act: -0.1700
Data Index: 7987045 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.5670. Min Act: -0.1700
Data Index: 7894150 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.5045. Min Act: -0.1700
Data Index: 7291204 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.4733. Min Act: -0.1700
Data Index: 758668 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.5045. Min Act: -0.1700
Data Index: 397453 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.4420. Min Act: -0.1700
Data Index: 7076508 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.4733. Min Act: -0.1700
Data Index: 1888005 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.4420. Min Act: -0.1700
Data Index: 579173 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.4108. Min Act: -0.1700
Data Index: 3006110 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.4108. Min Act: -0.1700
Data Index: 8613654 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.4108. Min Act: -0.1700
Data Index: 8910 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.3483. Min Act: -0.1700
Data Index: 6088418 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.3795. Min Act: -0.1700
Data Index: 5785425 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.3795. Min Act: -0.1700
Data Index: 2891816 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.3795. Min Act: -0.1700
Data Index: 6593021 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.3483. Min Act: -0.1700
Data Index: 942827 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7858. Min Range: -5.7858
Max Act: 5.3170. Min Act: -0.1700
Data Index: 1407495 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19