Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 528 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.9491. Min Act: -0.1700
Data Index: 7282505 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.7304. Min Act: -0.1700
Data Index: 1667619 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.7304. Min Act: -0.1700
Data Index: 2658741 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.6366. Min Act: -0.1700
Data Index: 3621854 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.5741. Min Act: -0.1700
Data Index: 8655438 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.5429. Min Act: -0.1700
Data Index: 6357573 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.5116. Min Act: -0.1700
Data Index: 815701 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.4491. Min Act: -0.1700
Data Index: 8439133 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.4179. Min Act: -0.1700
Data Index: 7580366 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.4179. Min Act: -0.1700
Data Index: 6576628 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.4179. Min Act: -0.1700
Data Index: 4159319 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.4179. Min Act: -0.1700
Data Index: 8766499 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.3866. Min Act: -0.1700
Data Index: 3528983 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.3866. Min Act: -0.1700
Data Index: 7537176 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.3554. Min Act: -0.1700
Data Index: 1318280 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.3241. Min Act: -0.1700
Data Index: 7457294 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.3554. Min Act: -0.1700
Data Index: 5589296 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.3554. Min Act: -0.1700
Data Index: 1139547 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.3241. Min Act: -0.1700
Data Index: 3063143 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9491. Min Range: -5.9491
Max Act: 5.2929. Min Act: -0.1700
Data Index: 2880098 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19