Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3349 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.9717. Min Act: -0.1700
Data Index: 3343811 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.9092. Min Act: -0.1700
Data Index: 6468228 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.7998. Min Act: -0.1700
Data Index: 4229588 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.8154. Min Act: -0.1700
Data Index: 4197524 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.8154. Min Act: -0.1700
Data Index: 7106452 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.8154. Min Act: -0.1700
Data Index: 5477455 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.7528. Min Act: -0.1700
Data Index: 434456 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.7528. Min Act: -0.1700
Data Index: 1416264 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.7528. Min Act: -0.1700
Data Index: 255830 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.7372. Min Act: -0.1700
Data Index: 7378239 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.7216. Min Act: -0.1700
Data Index: 1534981 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.7216. Min Act: -0.1700
Data Index: 5757579 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.6903. Min Act: -0.1700
Data Index: 2637647 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.7059. Min Act: -0.1700
Data Index: 2368327 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.6903. Min Act: -0.1700
Data Index: 4197517 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.6746. Min Act: -0.1700
Data Index: 7635683 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.6277. Min Act: -0.1700
Data Index: 2782886 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.6277. Min Act: -0.1700
Data Index: 5752509 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.5964. Min Act: -0.1700
Data Index: 6622344 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9717. Min Range: -3.9717
Max Act: 3.5807. Min Act: -0.1700
Data Index: 2624777 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19