Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2098 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1265. Min Range: -9.1265
Max Act: 9.1265. Min Act: -0.1700
Data Index: 1542668 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.9390. Min Act: -0.1700
Data Index: 2953627 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.9390. Min Act: -0.1700
Data Index: 1378793 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.8140. Min Act: -0.1700
Data Index: 7831499 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.7515. Min Act: -0.1700
Data Index: 5944401 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.7515. Min Act: -0.1700
Data Index: 2887583 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.7515. Min Act: -0.1700
Data Index: 6585156 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.6890. Min Act: -0.1700
Data Index: 530188 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.6265. Min Act: -0.1700
Data Index: 7582111 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.5640. Min Act: -0.1700
Data Index: 4825741 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.5640. Min Act: -0.1700
Data Index: 8497382 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.5640. Min Act: -0.1700
Data Index: 329650 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.6265. Min Act: -0.1700
Data Index: 423722 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.5640. Min Act: -0.1700
Data Index: 6577669 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.5640. Min Act: -0.1700
Data Index: 5910268 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.5015. Min Act: -0.1700
Data Index: 497273 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.5015. Min Act: -0.1700
Data Index: 6065148 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.5015. Min Act: -0.1700
Data Index: 790024 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.4390. Min Act: -0.1700
Data Index: 7116641 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1265. Min Range: -9.1265
Max Act: 8.4390. Min Act: -0.1700
Data Index: 1715271 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19