Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5448 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1136. Min Range: -4.1136
Max Act: 4.1136. Min Act: -0.1700
Data Index: 1878062 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1136. Min Range: -4.1136
Max Act: 4.0511. Min Act: -0.1700
Data Index: 2740546 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1136. Min Range: -4.1136
Max Act: 4.0199. Min Act: -0.1700
Data Index: 3645506 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9886. Min Act: -0.1700
Data Index: 2030882 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9573. Min Act: -0.1700
Data Index: 1501427 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9573. Min Act: -0.1700
Data Index: 5956056 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9261. Min Act: -0.1700
Data Index: 4286661 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9261. Min Act: -0.1700
Data Index: 2906395 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9261. Min Act: -0.1700
Data Index: 7638827 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9261. Min Act: -0.1700
Data Index: 6251300 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9261. Min Act: -0.1700
Data Index: 3580371 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9261. Min Act: -0.1700
Data Index: 1825133 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9261. Min Act: -0.1700
Data Index: 2270389 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9261. Min Act: -0.1700
Data Index: 3381362 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9261. Min Act: -0.1700
Data Index: 749332 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.9573. Min Act: -0.1700
Data Index: 4214606 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.8948. Min Act: -0.1700
Data Index: 6368538 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.8635. Min Act: -0.1700
Data Index: 5446833 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.8948. Min Act: -0.1700
Data Index: 5791509 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1136. Min Range: -4.1136
Max Act: 3.8635. Min Act: -0.1700
Data Index: 1136 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19