Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 798 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.5113. Min Act: -0.1700
Data Index: 23292 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.4801. Min Act: -0.1700
Data Index: 420347 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.4488. Min Act: -0.1700
Data Index: 6233152 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.3863. Min Act: -0.1700
Data Index: 420357 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.3551. Min Act: -0.1700
Data Index: 420350 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.3238. Min Act: -0.1700
Data Index: 420355 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.3238. Min Act: -0.1700
Data Index: 420354 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.3238. Min Act: -0.1700
Data Index: 4661470 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.2301. Min Act: -0.1700
Data Index: 420353 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.2301. Min Act: -0.1700
Data Index: 3727339 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1988. Min Act: -0.1700
Data Index: 8285953 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1988. Min Act: -0.1700
Data Index: 4099813 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1988. Min Act: -0.1700
Data Index: 904726 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1988. Min Act: -0.1700
Data Index: 420352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1988. Min Act: -0.1700
Data Index: 8294567 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1676. Min Act: -0.1700
Data Index: 994703 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1676. Min Act: -0.1700
Data Index: 5970326 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1676. Min Act: -0.1700
Data Index: 3798738 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1363. Min Act: -0.1700
Data Index: 4657505 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5113. Min Range: -5.5113
Max Act: 5.1676. Min Act: -0.1700
Data Index: 420358 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19