Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6898. Min Act: -0.1700
Data Index: 5550868 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6898. Min Act: -0.1700
Data Index: 1763623 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6898. Min Act: -0.1700
Data Index: 2689851 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6586. Min Act: -0.1700
Data Index: 378167 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6586. Min Act: -0.1700
Data Index: 5811805 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6586. Min Act: -0.1700
Data Index: 5161421 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6586. Min Act: -0.1700
Data Index: 8064128 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6586. Min Act: -0.1700
Data Index: 8203379 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6273. Min Act: -0.1700
Data Index: 195138 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.6273. Min Act: -0.1700
Data Index: 5151469 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5961. Min Act: -0.1700
Data Index: 3840321 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5648. Min Act: -0.1700
Data Index: 307678 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5648. Min Act: -0.1700
Data Index: 2847059 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5648. Min Act: -0.1700
Data Index: 366957 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5336. Min Act: -0.1700
Data Index: 7477106 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5648. Min Act: -0.1699
Data Index: 254858 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5648. Min Act: -0.1700
Data Index: 4336002 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5336. Min Act: -0.1700
Data Index: 1562141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5336. Min Act: -0.1700
Data Index: 2259546 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6898. Min Range: -4.6898
Max Act: 4.5336. Min Act: -0.1700
Data Index: 6973493 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19