Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4245 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0717. Min Range: -7.0717
Max Act: 7.0717. Min Act: -0.1700
Data Index: 3291340 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.8842. Min Act: -0.1700
Data Index: 3902732 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.8842. Min Act: -0.1700
Data Index: 5183276 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.8217. Min Act: -0.1700
Data Index: 8574251 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7905. Min Act: -0.1700
Data Index: 8800106 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.8217. Min Act: -0.1700
Data Index: 7002461 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7905. Min Act: -0.1700
Data Index: 7185747 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.7280. Min Act: -0.1700
Data Index: 6368248 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 5178917 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 17912 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 4863051 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 5533926 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6655. Min Act: -0.1700
Data Index: 2539776 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6655. Min Act: -0.1700
Data Index: 4761631 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6655. Min Act: -0.1700
Data Index: 8728657 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 6674152 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6967. Min Act: -0.1700
Data Index: 8483138 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6655. Min Act: -0.1700
Data Index: 8235951 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6655. Min Act: -0.1700
Data Index: 8212419 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0717. Min Range: -7.0717
Max Act: 6.6655. Min Act: -0.1700
Data Index: 2791572 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19