Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4176 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0273. Min Range: -5.0273
Max Act: 5.0273. Min Act: -0.1700
Data Index: 8132705 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.9960. Min Act: -0.1700
Data Index: 5830528 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0273. Min Range: -5.0273
Max Act: 5.0273. Min Act: -0.1700
Data Index: 2733272 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.9960. Min Act: -0.1700
Data Index: 487085 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.9960. Min Act: -0.1700
Data Index: 1903433 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.9648. Min Act: -0.1700
Data Index: 5393436 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.9335. Min Act: -0.1700
Data Index: 7431763 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.9023. Min Act: -0.1700
Data Index: 2934495 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.9023. Min Act: -0.1700
Data Index: 2249285 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.9023. Min Act: -0.1700
Data Index: 4853136 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.8710. Min Act: -0.1700
Data Index: 1367683 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.8710. Min Act: -0.1700
Data Index: 275778 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.8710. Min Act: -0.1700
Data Index: 7845943 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.9023. Min Act: -0.1700
Data Index: 178371 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.8085. Min Act: -0.1700
Data Index: 2879017 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.8398. Min Act: -0.1700
Data Index: 1830290 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.8398. Min Act: -0.1700
Data Index: 204618 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.8398. Min Act: -0.1700
Data Index: 7072319 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.8710. Min Act: -0.1700
Data Index: 1092768 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0273. Min Range: -5.0273
Max Act: 4.8398. Min Act: -0.1700
Data Index: 6307267 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19