Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5086 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.9131. Min Act: -0.1700
Data Index: 7171387 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.9444. Min Act: -0.1700
Data Index: 278482 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.8819. Min Act: -0.1700
Data Index: 1507731 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.8819. Min Act: -0.1700
Data Index: 8411998 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.8194. Min Act: -0.1700
Data Index: 3317871 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.8506. Min Act: -0.1700
Data Index: 6953312 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.7569. Min Act: -0.1700
Data Index: 2799578 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.7569. Min Act: -0.1700
Data Index: 1200259 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.6944. Min Act: -0.1700
Data Index: 3256349 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.6944. Min Act: -0.1700
Data Index: 4768222 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.6944. Min Act: -0.1700
Data Index: 4703862 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.6631. Min Act: -0.1700
Data Index: 8813877 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.6631. Min Act: -0.1700
Data Index: 5066560 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.6631. Min Act: -0.1700
Data Index: 4395110 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.6319. Min Act: -0.1700
Data Index: 2842678 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.6006. Min Act: -0.1700
Data Index: 430926 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.5694. Min Act: -0.1700
Data Index: 3687651 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.5694. Min Act: -0.1700
Data Index: 6202897 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.5381. Min Act: -0.1700
Data Index: 5610355 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9444. Min Range: -6.9444
Max Act: 6.5381. Min Act: -0.1700
Data Index: 3848640 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19