Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3932 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1114. Min Range: -5.1114
Max Act: 5.1114. Min Act: -0.1700
Data Index: 6426896 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1114. Min Range: -5.1114
Max Act: 5.0801. Min Act: -0.1700
Data Index: 258758 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1114. Min Range: -5.1114
Max Act: 5.0801. Min Act: -0.1700
Data Index: 6873652 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1114. Min Range: -5.1114
Max Act: 5.0489. Min Act: -0.1700
Data Index: 1417827 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1114. Min Range: -5.1114
Max Act: 5.0489. Min Act: -0.1700
Data Index: 3298775 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1114. Min Range: -5.1114
Max Act: 5.0176. Min Act: -0.1700
Data Index: 7812266 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1114. Min Range: -5.1114
Max Act: 5.0176. Min Act: -0.1700
Data Index: 6771718 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9864. Min Act: -0.1700
Data Index: 2725157 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9551. Min Act: -0.1700
Data Index: 3019450 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9551. Min Act: -0.1700
Data Index: 4712723 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9551. Min Act: -0.1700
Data Index: 1228652 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9551. Min Act: -0.1700
Data Index: 177384 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9551. Min Act: -0.1700
Data Index: 2650633 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9239. Min Act: -0.1700
Data Index: 6848773 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9239. Min Act: -0.1700
Data Index: 1704584 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.8926. Min Act: -0.1700
Data Index: 2785570 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9239. Min Act: -0.1700
Data Index: 2650277 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9239. Min Act: -0.1700
Data Index: 1494829 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9239. Min Act: -0.1700
Data Index: 2649368 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9239. Min Act: -0.1700
Data Index: 5260915 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19