Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0991. Min Range: -7.0991
Max Act: 7.0991. Min Act: -0.1700
Data Index: 6080198 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0991. Min Range: -7.0991
Max Act: 7.0366. Min Act: -0.1700
Data Index: 344924 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.9741. Min Act: -0.1700
Data Index: 8576621 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.9116. Min Act: -0.1700
Data Index: 4247625 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.9116. Min Act: -0.1700
Data Index: 4464625 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.9116. Min Act: -0.1700
Data Index: 4500901 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.8491. Min Act: -0.1700
Data Index: 3696605 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.8491. Min Act: -0.1700
Data Index: 2061716 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.8491. Min Act: -0.1700
Data Index: 5203121 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.8491. Min Act: -0.1700
Data Index: 8600397 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.8491. Min Act: -0.1700
Data Index: 1423149 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.8491. Min Act: -0.1700
Data Index: 8007028 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.8491. Min Act: -0.1700
Data Index: 6080202 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.8491. Min Act: -0.1700
Data Index: 1154533 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.7866. Min Act: -0.1700
Data Index: 415370 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.7866. Min Act: -0.1700
Data Index: 1738504 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.7866. Min Act: -0.1700
Data Index: 4935134 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.7866. Min Act: -0.1700
Data Index: 5830528 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.7866. Min Act: -0.1700
Data Index: 5928165 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0991. Min Range: -7.0991
Max Act: 6.7866. Min Act: -0.1700
Data Index: 1066398 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19