Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3752 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3172. Min Range: -8.3172
Max Act: 8.3172. Min Act: -0.1700
Data Index: 2046338 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3172. Min Range: -8.3172
Max Act: 8.1922. Min Act: -0.1700
Data Index: 2020746 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3172. Min Range: -8.3172
Max Act: 8.0672. Min Act: -0.1700
Data Index: 743922 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3172. Min Range: -8.3172
Max Act: 8.0672. Min Act: -0.1700
Data Index: 6424008 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3172. Min Range: -8.3172
Max Act: 8.0047. Min Act: -0.1700
Data Index: 1230187 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.9422. Min Act: -0.1700
Data Index: 3849149 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.8797. Min Act: -0.1700
Data Index: 2751167 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.8172. Min Act: -0.1700
Data Index: 2683406 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.7547. Min Act: -0.1700
Data Index: 2897941 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.6922. Min Act: -0.1700
Data Index: 5919272 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.6922. Min Act: -0.1700
Data Index: 1980599 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.6922. Min Act: -0.1700
Data Index: 297199 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.6297. Min Act: -0.1700
Data Index: 2610968 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.6297. Min Act: -0.1700
Data Index: 2874177 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.6297. Min Act: -0.1700
Data Index: 551649 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.6922. Min Act: -0.1700
Data Index: 5485611 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.6297. Min Act: -0.1700
Data Index: 5463020 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.6922. Min Act: -0.1700
Data Index: 2689938 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.5672. Min Act: -0.1700
Data Index: 5292226 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3172. Min Range: -8.3172
Max Act: 7.5672. Min Act: -0.1700
Data Index: 4481710 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19