Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 215 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0704. Min Range: -4.0704
Max Act: 4.0704. Min Act: -0.1700
Data Index: 7236767 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8516. Min Act: -0.1700
Data Index: 6070555 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.8203. Min Act: -0.1700
Data Index: 8082568 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.7421. Min Act: -0.1700
Data Index: 499466 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.6952. Min Act: -0.1700
Data Index: 8049538 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.6795. Min Act: -0.1700
Data Index: 5604934 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.6952. Min Act: -0.1700
Data Index: 7180387 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.6639. Min Act: -0.1700
Data Index: 3372679 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.6795. Min Act: -0.1700
Data Index: 6695300 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.6169. Min Act: -0.1700
Data Index: 5290777 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.6013. Min Act: -0.1700
Data Index: 148053 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.6013. Min Act: -0.1700
Data Index: 7756521 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.5700. Min Act: -0.1700
Data Index: 4361625 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.5700. Min Act: -0.1700
Data Index: 8203298 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.5543. Min Act: -0.1700
Data Index: 7203033 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.5543. Min Act: -0.1700
Data Index: 8506433 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.5387. Min Act: -0.1700
Data Index: 8093944 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.5387. Min Act: -0.1700
Data Index: 2891642 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.5387. Min Act: -0.1700
Data Index: 7522872 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0704. Min Range: -4.0704
Max Act: 3.5230. Min Act: -0.1700
Data Index: 3720287 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19