Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4793 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.8564. Min Act: -0.1700
Data Index: 74316 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.5439. Min Act: -0.1700
Data Index: 6290455 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.5126. Min Act: -0.1700
Data Index: 6565076 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.5126. Min Act: -0.1700
Data Index: 3694532 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4814. Min Act: -0.1700
Data Index: 3152792 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4814. Min Act: -0.1700
Data Index: 6046987 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4814. Min Act: -0.1700
Data Index: 2260375 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4501. Min Act: -0.1700
Data Index: 6000836 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4501. Min Act: -0.1700
Data Index: 8765245 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4501. Min Act: -0.1700
Data Index: 6923776 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4501. Min Act: -0.1700
Data Index: 5145692 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4501. Min Act: -0.1700
Data Index: 2578299 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4189. Min Act: -0.1700
Data Index: 1213737 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4189. Min Act: -0.1700
Data Index: 7441282 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4189. Min Act: -0.1700
Data Index: 6707464 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4189. Min Act: -0.1700
Data Index: 2033669 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.4189. Min Act: -0.1700
Data Index: 2123596 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.3876. Min Act: -0.1700
Data Index: 6116787 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.3876. Min Act: -0.1700
Data Index: 4789095 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8564. Min Range: -4.8564
Max Act: 4.3876. Min Act: -0.1700
Data Index: 6529674 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19