Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5070 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.9720. Min Act: -0.1700
Data Index: 697932 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.8157. Min Act: -0.1700
Data Index: 5443052 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.7532. Min Act: -0.1700
Data Index: 8514746 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.7532. Min Act: -0.1700
Data Index: 52048 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.7220. Min Act: -0.1700
Data Index: 1334734 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.7220. Min Act: -0.1700
Data Index: 2863827 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.6907. Min Act: -0.1700
Data Index: 1689909 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.6282. Min Act: -0.1700
Data Index: 925910 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5970. Min Act: -0.1700
Data Index: 6597313 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5970. Min Act: -0.1700
Data Index: 3579233 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5657. Min Act: -0.1700
Data Index: 1492195 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5970. Min Act: -0.1700
Data Index: 2907170 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5970. Min Act: -0.1700
Data Index: 2523275 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5657. Min Act: -0.1700
Data Index: 6558229 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5345. Min Act: -0.1700
Data Index: 681042 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5345. Min Act: -0.1700
Data Index: 6678854 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5345. Min Act: -0.1700
Data Index: 5552012 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5032. Min Act: -0.1700
Data Index: 705862 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5345. Min Act: -0.1700
Data Index: 4980268 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9720. Min Range: -4.9720
Max Act: 4.5032. Min Act: -0.1700
Data Index: 6928274 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19