Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5901 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.4375. Min Act: -0.1700
Data Index: 2361889 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.4375. Min Act: -0.1700
Data Index: 7801412 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.3750. Min Act: -0.1700
Data Index: 5189340 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.3750. Min Act: -0.1700
Data Index: 8533382 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.3750. Min Act: -0.1700
Data Index: 62741 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.3125. Min Act: -0.1700
Data Index: 1812652 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.3125. Min Act: -0.1700
Data Index: 6689502 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.2500. Min Act: -0.1700
Data Index: 436738 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.1875. Min Act: -0.1700
Data Index: 5822309 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.1250. Min Act: -0.1700
Data Index: 1730996 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.1250. Min Act: -0.1700
Data Index: 4566256 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.1250. Min Act: -0.1700
Data Index: 980097 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.1250. Min Act: -0.1700
Data Index: 6009803 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.1250. Min Act: -0.1700
Data Index: 6769371 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.1250. Min Act: -0.1700
Data Index: 5734068 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.0625. Min Act: -0.1700
Data Index: 6653710 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.0625. Min Act: -0.1700
Data Index: 981415 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.0625. Min Act: -0.1700
Data Index: 891649 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.0625. Min Act: -0.1700
Data Index: 6539231 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4375. Min Range: -9.4375
Max Act: 9.0625. Min Act: -0.1700
Data Index: 2700995 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19