Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.5378. Min Act: -0.1700
Data Index: 8379275 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.5065. Min Act: -0.1700
Data Index: 7618740 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.5378. Min Act: -0.1700
Data Index: 8475041 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.5065. Min Act: -0.1700
Data Index: 7982403 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4753. Min Act: -0.1700
Data Index: 8514189 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4753. Min Act: -0.1700
Data Index: 5065650 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4753. Min Act: -0.1700
Data Index: 259108 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4440. Min Act: -0.1700
Data Index: 8752178 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4440. Min Act: -0.1700
Data Index: 189217 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4440. Min Act: -0.1700
Data Index: 8472470 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4128. Min Act: -0.1700
Data Index: 5065649 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4128. Min Act: -0.1700
Data Index: 189211 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4128. Min Act: -0.1700
Data Index: 6393721 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4128. Min Act: -0.1700
Data Index: 1591149 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4128. Min Act: -0.1700
Data Index: 7452525 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4128. Min Act: -0.1700
Data Index: 472175 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.4128. Min Act: -0.1700
Data Index: 5032420 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.3815. Min Act: -0.1700
Data Index: 5243871 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.3815. Min Act: -0.1700
Data Index: 8031943 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5378. Min Range: -4.5378
Max Act: 4.3815. Min Act: -0.1700
Data Index: 6644893 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19