Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5319 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1631. Min Range: -5.1631
Max Act: 5.1631. Min Act: -0.1700
Data Index: 18690 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1631. Min Range: -5.1631
Max Act: 5.1319. Min Act: -0.1700
Data Index: 8811877 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1631. Min Range: -5.1631
Max Act: 5.0381. Min Act: -0.1700
Data Index: 4068594 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1631. Min Range: -5.1631
Max Act: 5.0069. Min Act: -0.1700
Data Index: 4103934 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.9756. Min Act: -0.1700
Data Index: 8734240 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.9444. Min Act: -0.1700
Data Index: 2466617 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.9444. Min Act: -0.1700
Data Index: 4344674 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.9444. Min Act: -0.1700
Data Index: 1801497 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.9131. Min Act: -0.1700
Data Index: 1288013 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8819. Min Act: -0.1700
Data Index: 2628359 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8819. Min Act: -0.1700
Data Index: 4094300 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8819. Min Act: -0.1700
Data Index: 3537864 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8819. Min Act: -0.1700
Data Index: 8736266 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8506. Min Act: -0.1700
Data Index: 8734340 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8819. Min Act: -0.1700
Data Index: 2066900 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8819. Min Act: -0.1700
Data Index: 488385 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8506. Min Act: -0.1700
Data Index: 607690 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8194. Min Act: -0.1700
Data Index: 839661 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8819. Min Act: -0.1700
Data Index: 1869513 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1631. Min Range: -5.1631
Max Act: 4.8506. Min Act: -0.1700
Data Index: 4094302 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19