Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4569. Min Range: -6.4569
Max Act: 6.4569. Min Act: -0.1700
Data Index: 6011030 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4569. Min Range: -6.4569
Max Act: 6.2694. Min Act: -0.1700
Data Index: 3632486 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4569. Min Range: -6.4569
Max Act: 6.2381. Min Act: -0.1700
Data Index: 3357156 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4569. Min Range: -6.4569
Max Act: 6.1756. Min Act: -0.1700
Data Index: 8590737 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4569. Min Range: -6.4569
Max Act: 6.1444. Min Act: -0.1700
Data Index: 8379778 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4569. Min Range: -6.4569
Max Act: 6.0819. Min Act: -0.1700
Data Index: 632944 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.9569. Min Act: -0.1700
Data Index: 6457795 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.9569. Min Act: -0.1700
Data Index: 3912344 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.9569. Min Act: -0.1700
Data Index: 5446356 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.9256. Min Act: -0.1700
Data Index: 1467483 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.9569. Min Act: -0.1700
Data Index: 7789760 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.9256. Min Act: -0.1700
Data Index: 643823 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.9256. Min Act: -0.1700
Data Index: 2835755 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.9256. Min Act: -0.1700
Data Index: 8028443 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.8944. Min Act: -0.1700
Data Index: 297122 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.8944. Min Act: -0.1700
Data Index: 2002887 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.8631. Min Act: -0.1700
Data Index: 5774848 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.8319. Min Act: -0.1700
Data Index: 1495927 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.8319. Min Act: -0.1700
Data Index: 4261219 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4569. Min Range: -6.4569
Max Act: 5.8319. Min Act: -0.1700
Data Index: 7752511 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19