Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.7361. Min Act: -0.1700
Data Index: 3914443 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.7048. Min Act: -0.1700
Data Index: 8549910 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.7048. Min Act: -0.1700
Data Index: 8693584 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.6735. Min Act: -0.1700
Data Index: 7732193 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.6735. Min Act: -0.1700
Data Index: 3897511 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.6422. Min Act: -0.1700
Data Index: 4365799 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5796. Min Act: -0.1700
Data Index: 2127071 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5796. Min Act: -0.1700
Data Index: 3141336 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5796. Min Act: -0.1700
Data Index: 6515068 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5796. Min Act: -0.1700
Data Index: 5603203 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5483. Min Act: -0.1700
Data Index: 6989272 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5483. Min Act: -0.1700
Data Index: 1248544 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5483. Min Act: -0.1700
Data Index: 2516940 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5170. Min Act: -0.1700
Data Index: 3746232 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5170. Min Act: -0.1700
Data Index: 2077134 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5170. Min Act: -0.1700
Data Index: 5083825 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5170. Min Act: -0.1700
Data Index: 8323381 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5170. Min Act: -0.1700
Data Index: 6818539 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.5170. Min Act: -0.1700
Data Index: 200301 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7361. Min Range: -3.7361
Max Act: 3.4857. Min Act: -0.1700
Data Index: 8286528 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19