Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4047 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.8450. Min Act: -0.1700
Data Index: 7523951 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.7512. Min Act: -0.1700
Data Index: 3086353 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.7200. Min Act: -0.1700
Data Index: 2736723 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.6575. Min Act: -0.1700
Data Index: 4793105 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.6262. Min Act: -0.1700
Data Index: 5060983 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.5637. Min Act: -0.1700
Data Index: 835579 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.5325. Min Act: -0.1700
Data Index: 8225153 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.5325. Min Act: -0.1700
Data Index: 7319871 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.5012. Min Act: -0.1700
Data Index: 7350705 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.5012. Min Act: -0.1700
Data Index: 984674 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.5012. Min Act: -0.1700
Data Index: 1526057 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4700. Min Act: -0.1700
Data Index: 4867594 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4700. Min Act: -0.1700
Data Index: 3803277 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4700. Min Act: -0.1700
Data Index: 2378013 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4700. Min Act: -0.1700
Data Index: 4830865 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 5246806 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 1232754 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 1756780 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 383741 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8450. Min Range: -5.8450
Max Act: 5.4387. Min Act: -0.1700
Data Index: 430523 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19