Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 420 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.7217. Min Act: -0.1700
Data Index: 3318461 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.6904. Min Act: -0.1700
Data Index: 8098462 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.6279. Min Act: -0.1700
Data Index: 5423769 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.6592. Min Act: -0.1700
Data Index: 317163 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.5967. Min Act: -0.1700
Data Index: 1374410 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.4717. Min Act: -0.1700
Data Index: 4973942 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.4092. Min Act: -0.1700
Data Index: 7023797 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.4717. Min Act: -0.1700
Data Index: 5036442 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.4404. Min Act: -0.1700
Data Index: 8231249 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.4404. Min Act: -0.1700
Data Index: 631983 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.4092. Min Act: -0.1700
Data Index: 4424894 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.3779. Min Act: -0.1700
Data Index: 390390 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.3779. Min Act: -0.1700
Data Index: 5834191 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.3467. Min Act: -0.1700
Data Index: 4420358 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.3154. Min Act: -0.1700
Data Index: 6658572 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.2842. Min Act: -0.1700
Data Index: 2229437 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.3154. Min Act: -0.1700
Data Index: 1260133 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.2842. Min Act: -0.1700
Data Index: 5917345 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.2842. Min Act: -0.1700
Data Index: 4671294 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7217. Min Range: -5.7217
Max Act: 5.2842. Min Act: -0.1700
Data Index: 7203489 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19