Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.7014. Min Act: -0.1700
Data Index: 5977034 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.6076. Min Act: -0.1700
Data Index: 2360274 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.5764. Min Act: -0.1700
Data Index: 5969604 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.2951. Min Act: -0.1700
Data Index: 167409 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.2014. Min Act: -0.1700
Data Index: 4781370 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.2326. Min Act: -0.1700
Data Index: 5347490 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.2014. Min Act: -0.1700
Data Index: 8613359 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1701. Min Act: -0.1700
Data Index: 5185382 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1701. Min Act: -0.1700
Data Index: 5819349 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1701. Min Act: -0.1700
Data Index: 438081 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1701. Min Act: -0.1700
Data Index: 5683988 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1701. Min Act: -0.1700
Data Index: 4328517 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1389. Min Act: -0.1700
Data Index: 5436970 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1389. Min Act: -0.1700
Data Index: 7536145 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1389. Min Act: -0.1700
Data Index: 2840829 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1076. Min Act: -0.1700
Data Index: 4735975 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1076. Min Act: -0.1700
Data Index: 7686726 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1076. Min Act: -0.1700
Data Index: 2734308 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.1076. Min Act: -0.1700
Data Index: 7032255 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7014. Min Range: -7.7014
Max Act: 7.0764. Min Act: -0.1700
Data Index: 360611 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19