Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4106 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.8444. Min Act: -0.1700
Data Index: 4083199 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.7819. Min Act: -0.1700
Data Index: 8488034 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.7506. Min Act: -0.1700
Data Index: 4277488 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.7194. Min Act: -0.1700
Data Index: 6025749 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.6881. Min Act: -0.1700
Data Index: 180499 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.6569. Min Act: -0.1700
Data Index: 3079033 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.6569. Min Act: -0.1700
Data Index: 8426819 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.6256. Min Act: -0.1700
Data Index: 3945276 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.6256. Min Act: -0.1700
Data Index: 1125629 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.6256. Min Act: -0.1700
Data Index: 4517705 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.6256. Min Act: -0.1700
Data Index: 8814083 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.6256. Min Act: -0.1700
Data Index: 6093006 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.6256. Min Act: -0.1700
Data Index: 1615408 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.5631. Min Act: -0.1700
Data Index: 1264275 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.5944. Min Act: -0.1700
Data Index: 7710575 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.5631. Min Act: -0.1700
Data Index: 211551 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.5319. Min Act: -0.1700
Data Index: 7979920 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.5319. Min Act: -0.1700
Data Index: 211539 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.5319. Min Act: -0.1700
Data Index: 5218392 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8444. Min Range: -5.8444
Max Act: 5.5319. Min Act: -0.1700
Data Index: 8102450 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19