Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3745 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1545. Min Range: -7.1545
Max Act: 7.1545. Min Act: -0.1700
Data Index: 8027833 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1545. Min Range: -7.1545
Max Act: 7.0920. Min Act: -0.1700
Data Index: 7812321 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.8420. Min Act: -0.1700
Data Index: 657652 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7795. Min Act: -0.1700
Data Index: 5904570 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.8107. Min Act: -0.1700
Data Index: 4162737 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.8107. Min Act: -0.1700
Data Index: 973126 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.8107. Min Act: -0.1700
Data Index: 1562483 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.8107. Min Act: -0.1700
Data Index: 1198843 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.8107. Min Act: -0.1700
Data Index: 252990 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7795. Min Act: -0.1700
Data Index: 5378465 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7482. Min Act: -0.1700
Data Index: 2353046 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7795. Min Act: -0.1700
Data Index: 7068959 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7795. Min Act: -0.1700
Data Index: 6788371 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7482. Min Act: -0.1700
Data Index: 3060613 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7482. Min Act: -0.1700
Data Index: 4942722 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7482. Min Act: -0.1700
Data Index: 88537 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.6857. Min Act: -0.1700
Data Index: 2864141 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7170. Min Act: -0.1700
Data Index: 409712 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7170. Min Act: -0.1700
Data Index: 1906060 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1545. Min Range: -7.1545
Max Act: 6.7170. Min Act: -0.1700
Data Index: 6460442 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19