Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.9803. Min Act: -0.1700
Data Index: 189323 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.9803. Min Act: -0.1700
Data Index: 8757564 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.9803. Min Act: -0.1700
Data Index: 4315757 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.9491. Min Act: -0.1700
Data Index: 7636762 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.9178. Min Act: -0.1700
Data Index: 4444330 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.9178. Min Act: -0.1700
Data Index: 2340728 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8866. Min Act: -0.1700
Data Index: 3364415 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8866. Min Act: -0.1700
Data Index: 7135827 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8866. Min Act: -0.1700
Data Index: 7660655 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8553. Min Act: -0.1700
Data Index: 3270851 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8553. Min Act: -0.1700
Data Index: 922831 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8866. Min Act: -0.1700
Data Index: 294013 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8553. Min Act: -0.1700
Data Index: 5716343 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.7928. Min Act: -0.1700
Data Index: 8171037 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8241. Min Act: -0.1700
Data Index: 7978378 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8241. Min Act: -0.1700
Data Index: 8560304 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8241. Min Act: -0.1700
Data Index: 4623206 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.8241. Min Act: -0.1700
Data Index: 5831796 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.7928. Min Act: -0.1700
Data Index: 3929437 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9803. Min Range: -4.9803
Max Act: 4.7928. Min Act: -0.1700
Data Index: 7636761 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19