Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1003 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.6031. Min Act: -0.1700
Data Index: 2168793 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.4156. Min Act: -0.1700
Data Index: 3913930 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.2593. Min Act: -0.1700
Data Index: 5114007 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.1656. Min Act: -0.1700
Data Index: 6244847 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.1343. Min Act: -0.1700
Data Index: 1662843 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.1656. Min Act: -0.1700
Data Index: 239646 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.1031. Min Act: -0.1700
Data Index: 998952 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.1031. Min Act: -0.1700
Data Index: 2870752 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.0718. Min Act: -0.1700
Data Index: 4868568 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.0718. Min Act: -0.1700
Data Index: 7392406 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.0718. Min Act: -0.1700
Data Index: 8121340 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6031. Min Range: -8.6031
Max Act: 8.0093. Min Act: -0.1700
Data Index: 5896980 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6031. Min Range: -8.6031
Max Act: 7.9781. Min Act: -0.1700
Data Index: 465027 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6031. Min Range: -8.6031
Max Act: 7.9781. Min Act: -0.1700
Data Index: 1229741 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6031. Min Range: -8.6031
Max Act: 7.9468. Min Act: -0.1700
Data Index: 41594 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6031. Min Range: -8.6031
Max Act: 7.9468. Min Act: -0.1700
Data Index: 6937847 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6031. Min Range: -8.6031
Max Act: 7.9156. Min Act: -0.1700
Data Index: 2644365 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6031. Min Range: -8.6031
Max Act: 7.8843. Min Act: -0.1700
Data Index: 3067571 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6031. Min Range: -8.6031
Max Act: 7.9156. Min Act: -0.1700
Data Index: 3650354 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6031. Min Range: -8.6031
Max Act: 7.9156. Min Act: -0.1700
Data Index: 1238400 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19