Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5511 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1833. Min Range: -5.1833
Max Act: 5.1833. Min Act: -0.1700
Data Index: 3703275 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1833. Min Range: -5.1833
Max Act: 5.0583. Min Act: -0.1700
Data Index: 3382167 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.8395. Min Act: -0.1700
Data Index: 7594685 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.7770. Min Act: -0.1700
Data Index: 6666327 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.7458. Min Act: -0.1700
Data Index: 3307460 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.7458. Min Act: -0.1700
Data Index: 4028165 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.7145. Min Act: -0.1700
Data Index: 4028275 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.6833. Min Act: -0.1700
Data Index: 4213613 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.6520. Min Act: -0.1700
Data Index: 2345636 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.6520. Min Act: -0.1700
Data Index: 7060044 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.6520. Min Act: -0.1700
Data Index: 4973189 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.6520. Min Act: -0.1700
Data Index: 3543203 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.6208. Min Act: -0.1700
Data Index: 881380 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.6208. Min Act: -0.1700
Data Index: 3858435 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.6208. Min Act: -0.1700
Data Index: 4826523 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.5895. Min Act: -0.1700
Data Index: 6211874 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.5583. Min Act: -0.1700
Data Index: 2961274 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.5270. Min Act: -0.1700
Data Index: 2506989 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.5270. Min Act: -0.1700
Data Index: 6666330 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1833. Min Range: -5.1833
Max Act: 4.5270. Min Act: -0.1700
Data Index: 6325388 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19