Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4323 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2324. Min Range: -4.2324
Max Act: 4.2324. Min Act: -0.1700
Data Index: 5293555 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2324. Min Range: -4.2324
Max Act: 4.0761. Min Act: -0.1700
Data Index: 5338387 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2324. Min Range: -4.2324
Max Act: 4.0761. Min Act: -0.1700
Data Index: 3019965 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2324. Min Range: -4.2324
Max Act: 4.0136. Min Act: -0.1700
Data Index: 2721817 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.9823. Min Act: -0.1700
Data Index: 6387309 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.9198. Min Act: -0.1700
Data Index: 6372980 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.9511. Min Act: -0.1700
Data Index: 7141378 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.9511. Min Act: -0.1700
Data Index: 1287441 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.9198. Min Act: -0.1700
Data Index: 2773878 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.9198. Min Act: -0.1700
Data Index: 2404750 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.9198. Min Act: -0.1700
Data Index: 6832895 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.8886. Min Act: -0.1700
Data Index: 4390177 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.8886. Min Act: -0.1700
Data Index: 3385087 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.8886. Min Act: -0.1700
Data Index: 2051898 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.8886. Min Act: -0.1700
Data Index: 1713894 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.8886. Min Act: -0.1700
Data Index: 5070 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.8886. Min Act: -0.1700
Data Index: 5208700 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.8886. Min Act: -0.1700
Data Index: 1438407 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.8573. Min Act: -0.1700
Data Index: 4141059 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2324. Min Range: -4.2324
Max Act: 3.8573. Min Act: -0.1700
Data Index: 1566209 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19