Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.6196. Min Act: -0.1700
Data Index: 6935486 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.5883. Min Act: -0.1700
Data Index: 795641 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.5571. Min Act: -0.1700
Data Index: 8504459 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.4321. Min Act: -0.1700
Data Index: 8228859 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.4008. Min Act: -0.1700
Data Index: 4314568 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.3383. Min Act: -0.1700
Data Index: 8325341 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.3383. Min Act: -0.1700
Data Index: 7309136 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.3071. Min Act: -0.1700
Data Index: 3700364 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.3383. Min Act: -0.1700
Data Index: 7447697 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.2758. Min Act: -0.1700
Data Index: 4628823 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.2133. Min Act: -0.1700
Data Index: 4146987 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.1821. Min Act: -0.1700
Data Index: 7350041 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.1821. Min Act: -0.1700
Data Index: 2586744 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.2133. Min Act: -0.1700
Data Index: 6165289 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.1821. Min Act: -0.1700
Data Index: 7540529 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.1821. Min Act: -0.1700
Data Index: 1746820 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.1821. Min Act: -0.1700
Data Index: 8345693 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.1821. Min Act: -0.1700
Data Index: 1978882 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.1821. Min Act: -0.1700
Data Index: 1735895 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6196. Min Range: -6.6196
Max Act: 6.1821. Min Act: -0.1700
Data Index: 1952776 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19