Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3963 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.2288. Min Act: -0.1700
Data Index: 701740 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.1351. Min Act: -0.1700
Data Index: 2399723 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.1351. Min Act: -0.1700
Data Index: 4084727 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0726. Min Act: -0.1700
Data Index: 2399721 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0726. Min Act: -0.1700
Data Index: 1611519 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0726. Min Act: -0.1700
Data Index: 8259502 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0726. Min Act: -0.1700
Data Index: 2399710 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0726. Min Act: -0.1700
Data Index: 3799264 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0726. Min Act: -0.1700
Data Index: 8408827 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0413. Min Act: -0.1700
Data Index: 8259499 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0413. Min Act: -0.1700
Data Index: 4084735 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0101. Min Act: -0.1700
Data Index: 4266457 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0101. Min Act: -0.1700
Data Index: 1652650 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0101. Min Act: -0.1700
Data Index: 2215624 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2288. Min Range: -6.2288
Max Act: 6.0101. Min Act: -0.1700
Data Index: 906851 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2288. Min Range: -6.2288
Max Act: 5.9788. Min Act: -0.1700
Data Index: 3799268 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2288. Min Range: -6.2288
Max Act: 5.9788. Min Act: -0.1700
Data Index: 2659380 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2288. Min Range: -6.2288
Max Act: 5.9476. Min Act: -0.1700
Data Index: 4515987 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2288. Min Range: -6.2288
Max Act: 5.9163. Min Act: -0.1700
Data Index: 3966107 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2288. Min Range: -6.2288
Max Act: 5.9476. Min Act: -0.1700
Data Index: 8259500 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19