Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.6495. Min Act: -0.1700
Data Index: 1052564 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.5245. Min Act: -0.1700
Data Index: 4537364 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.4933. Min Act: -0.1700
Data Index: 986300 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.3370. Min Act: -0.1700
Data Index: 7704680 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.3058. Min Act: -0.1700
Data Index: 7410853 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.2433. Min Act: -0.1700
Data Index: 6454469 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.2433. Min Act: -0.1700
Data Index: 3635869 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.2433. Min Act: -0.1700
Data Index: 5258021 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.2120. Min Act: -0.1700
Data Index: 3095525 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.1808. Min Act: -0.1700
Data Index: 1553100 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.1808. Min Act: -0.1700
Data Index: 6954348 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.1808. Min Act: -0.1700
Data Index: 6569957 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.1183. Min Act: -0.1700
Data Index: 2867868 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.1495. Min Act: -0.1700
Data Index: 8115915 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.1183. Min Act: -0.1700
Data Index: 5382925 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.1183. Min Act: -0.1700
Data Index: 1543048 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.1183. Min Act: -0.1700
Data Index: 876428 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.1183. Min Act: -0.1700
Data Index: 399742 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.0870. Min Act: -0.1700
Data Index: 2805707 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6495. Min Range: -5.6495
Max Act: 5.0558. Min Act: -0.1700
Data Index: 6432455 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19