Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1335 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.4181. Min Act: -0.1700
Data Index: 8700094 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.3243. Min Act: -0.1700
Data Index: 6079069 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.1681. Min Act: -0.1700
Data Index: 5702062 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.1681. Min Act: -0.1700
Data Index: 5529955 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.1056. Min Act: -0.1700
Data Index: 8335650 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0743. Min Act: -0.1700
Data Index: 705542 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0431. Min Act: -0.1700
Data Index: 3383101 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.9493. Min Act: -0.1700
Data Index: 8249248 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.9181. Min Act: -0.1700
Data Index: 4723486 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.8556. Min Act: -0.1700
Data Index: 808290 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.8868. Min Act: -0.1700
Data Index: 3156597 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.8868. Min Act: -0.1700
Data Index: 7578727 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.8868. Min Act: -0.1700
Data Index: 4014998 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.8556. Min Act: -0.1700
Data Index: 4869377 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.8556. Min Act: -0.1700
Data Index: 2362527 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.8556. Min Act: -0.1700
Data Index: 1129803 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.7931. Min Act: -0.1700
Data Index: 4315581 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.8243. Min Act: -0.1700
Data Index: 2455787 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.8243. Min Act: -0.1700
Data Index: 5978714 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.7931. Min Act: -0.1700
Data Index: 2100539 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19