Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2595. Min Range: -7.2595
Max Act: 7.2595. Min Act: -0.1700
Data Index: 3566970 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2595. Min Range: -7.2595
Max Act: 7.1970. Min Act: -0.1700
Data Index: 4035830 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2595. Min Range: -7.2595
Max Act: 7.1657. Min Act: -0.1700
Data Index: 1635876 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2595. Min Range: -7.2595
Max Act: 7.1032. Min Act: -0.1700
Data Index: 1553967 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2595. Min Range: -7.2595
Max Act: 7.0720. Min Act: -0.1700
Data Index: 2835128 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2595. Min Range: -7.2595
Max Act: 7.0095. Min Act: -0.1700
Data Index: 6896213 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2595. Min Range: -7.2595
Max Act: 7.0095. Min Act: -0.1700
Data Index: 8624692 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9782. Min Act: -0.1700
Data Index: 5437476 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9782. Min Act: -0.1700
Data Index: 5556003 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9782. Min Act: -0.1700
Data Index: 5248643 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9782. Min Act: -0.1700
Data Index: 5241814 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9470. Min Act: -0.1700
Data Index: 4593984 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9470. Min Act: -0.1700
Data Index: 3005541 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 2658602 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 8185245 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 3602395 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.9157. Min Act: -0.1700
Data Index: 1947719 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.8845. Min Act: -0.1700
Data Index: 3258494 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.8845. Min Act: -0.1700
Data Index: 2021900 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2595. Min Range: -7.2595
Max Act: 6.8532. Min Act: -0.1700
Data Index: 7026662 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19