Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3783. Min Range: -9.3783
Max Act: 9.3783. Min Act: -0.1700
Data Index: 2492746 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3783. Min Range: -9.3783
Max Act: 9.1908. Min Act: -0.1700
Data Index: 8089220 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3783. Min Range: -9.3783
Max Act: 9.1908. Min Act: -0.1700
Data Index: 1001566 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3783. Min Range: -9.3783
Max Act: 9.1283. Min Act: -0.1700
Data Index: 1588804 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3783. Min Range: -9.3783
Max Act: 9.0658. Min Act: -0.1700
Data Index: 2041357 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3783. Min Range: -9.3783
Max Act: 9.0658. Min Act: -0.1700
Data Index: 533472 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3783. Min Range: -9.3783
Max Act: 9.0658. Min Act: -0.1700
Data Index: 3801017 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3783. Min Range: -9.3783
Max Act: 9.0658. Min Act: -0.1700
Data Index: 6805926 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.9408. Min Act: -0.1700
Data Index: 8830095 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.8783. Min Act: -0.1700
Data Index: 4109646 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.8783. Min Act: -0.1700
Data Index: 4942295 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.8783. Min Act: -0.1700
Data Index: 6351265 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.8158. Min Act: -0.1700
Data Index: 8708961 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.8783. Min Act: -0.1700
Data Index: 1218217 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.8158. Min Act: -0.1700
Data Index: 987975 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.7533. Min Act: -0.1700
Data Index: 6091241 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.7533. Min Act: -0.1700
Data Index: 6439675 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.7533. Min Act: -0.1700
Data Index: 7296544 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.6908. Min Act: -0.1700
Data Index: 4987382 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3783. Min Range: -9.3783
Max Act: 8.6908. Min Act: -0.1700
Data Index: 6805927 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19