Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1929 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1476. Min Range: -6.1476
Max Act: 6.1476. Min Act: -0.1700
Data Index: 3639499 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.9288. Min Act: -0.1700
Data Index: 3639497 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.8976. Min Act: -0.1700
Data Index: 6859635 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.8663. Min Act: -0.1700
Data Index: 5689865 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.8038. Min Act: -0.1700
Data Index: 3356922 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7413. Min Act: -0.1700
Data Index: 4744226 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7413. Min Act: -0.1700
Data Index: 2707520 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7726. Min Act: -0.1700
Data Index: 4037530 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7413. Min Act: -0.1700
Data Index: 3403717 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7413. Min Act: -0.1700
Data Index: 3478644 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6788. Min Act: -0.1700
Data Index: 8114214 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7101. Min Act: -0.1700
Data Index: 65397 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7413. Min Act: -0.1700
Data Index: 5882065 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7101. Min Act: -0.1700
Data Index: 420630 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6788. Min Act: -0.1700
Data Index: 357320 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6788. Min Act: -0.1700
Data Index: 4690716 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6788. Min Act: -0.1697
Data Index: 3940889 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7101. Min Act: -0.1689
Data Index: 6092580 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6788. Min Act: -0.1700
Data Index: 6956404 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6788. Min Act: -0.1700
Data Index: 1052222 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19