Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5726 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.9547. Min Act: -0.1700
Data Index: 4705170 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.7359. Min Act: -0.1700
Data Index: 7236121 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6734. Min Act: -0.1700
Data Index: 3063680 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6422. Min Act: -0.1700
Data Index: 856548 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6734. Min Act: -0.1700
Data Index: 1487566 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6109. Min Act: -0.1700
Data Index: 430217 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.5797. Min Act: -0.1700
Data Index: 4253623 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6109. Min Act: -0.1700
Data Index: 306864 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.6109. Min Act: -0.1700
Data Index: 2965926 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.5484. Min Act: -0.1700
Data Index: 2239287 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.5172. Min Act: -0.1700
Data Index: 6079422 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.5172. Min Act: -0.1700
Data Index: 659782 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.5172. Min Act: -0.1700
Data Index: 4800025 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.4546. Min Act: -0.1700
Data Index: 4532547 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.4546. Min Act: -0.1700
Data Index: 5918293 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.4546. Min Act: -0.1700
Data Index: 659784 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.4546. Min Act: -0.1700
Data Index: 55685 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.4234. Min Act: -0.1700
Data Index: 7680839 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.4234. Min Act: -0.1700
Data Index: 7680815 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9547. Min Range: -4.9547
Max Act: 4.3609. Min Act: -0.1700
Data Index: 7312334 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19