Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.5106. Min Act: -0.1700
Data Index: 1283305 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.4168. Min Act: -0.1700
Data Index: 3008000 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.4481. Min Act: -0.1700
Data Index: 4075741 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.4168. Min Act: -0.1700
Data Index: 6088550 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.3855. Min Act: -0.1700
Data Index: 5109355 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.2918. Min Act: -0.1700
Data Index: 2747034 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.2293. Min Act: -0.1700
Data Index: 921613 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.2293. Min Act: -0.1700
Data Index: 3693164 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1980. Min Act: -0.1700
Data Index: 2694176 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1980. Min Act: -0.1700
Data Index: 7273779 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1668. Min Act: -0.1700
Data Index: 5540776 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1668. Min Act: -0.1700
Data Index: 689259 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1668. Min Act: -0.1700
Data Index: 5071947 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1668. Min Act: -0.1700
Data Index: 3527095 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1668. Min Act: -0.1700
Data Index: 613172 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1668. Min Act: -0.1700
Data Index: 1681271 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1668. Min Act: -0.1700
Data Index: 6707992 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1668. Min Act: -0.1700
Data Index: 4317079 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1355. Min Act: -0.1700
Data Index: 7327382 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5106. Min Range: -4.5106
Max Act: 4.1043. Min Act: -0.1700
Data Index: 501191 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19