Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5013 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3547. Min Range: -7.3547
Max Act: 7.3547. Min Act: -0.1700
Data Index: 4989037 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3547. Min Range: -7.3547
Max Act: 7.1047. Min Act: -0.1700
Data Index: 6786748 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3547. Min Range: -7.3547
Max Act: 7.0422. Min Act: -0.1700
Data Index: 2999839 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3547. Min Range: -7.3547
Max Act: 7.0110. Min Act: -0.1700
Data Index: 926295 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.9172. Min Act: -0.1700
Data Index: 5250400 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.8860. Min Act: -0.1700
Data Index: 4871517 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.8547. Min Act: -0.1700
Data Index: 2979063 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.8547. Min Act: -0.1700
Data Index: 8564770 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.8547. Min Act: -0.1700
Data Index: 2331019 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.8547. Min Act: -0.1700
Data Index: 3314787 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7610. Min Act: -0.1700
Data Index: 379839 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7610. Min Act: -0.1700
Data Index: 3002420 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7922. Min Act: -0.1700
Data Index: 5755684 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7610. Min Act: -0.1700
Data Index: 5853630 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7610. Min Act: -0.1700
Data Index: 4308924 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7610. Min Act: -0.1700
Data Index: 4904397 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7610. Min Act: -0.1700
Data Index: 6689321 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7297. Min Act: -0.1700
Data Index: 710561 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7297. Min Act: -0.1700
Data Index: 1809939 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3547. Min Range: -7.3547
Max Act: 6.7297. Min Act: -0.1700
Data Index: 2171988 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19