Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 325 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4371. Min Range: -6.4371
Max Act: 6.4371. Min Act: -0.1700
Data Index: 82149 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4371. Min Range: -6.4371
Max Act: 6.1559. Min Act: -0.1700
Data Index: 266869 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.9684. Min Act: -0.1700
Data Index: 196768 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.9059. Min Act: -0.1700
Data Index: 8506343 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.8746. Min Act: -0.1700
Data Index: 6935461 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.8434. Min Act: -0.1700
Data Index: 1466808 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.8434. Min Act: -0.1700
Data Index: 6611031 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.8434. Min Act: -0.1700
Data Index: 4602172 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.8121. Min Act: -0.1700
Data Index: 5159424 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.7496. Min Act: -0.1700
Data Index: 3248497 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.7184. Min Act: -0.1700
Data Index: 3554950 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.7184. Min Act: -0.1700
Data Index: 7236753 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.7496. Min Act: -0.1700
Data Index: 5515448 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.7184. Min Act: -0.1700
Data Index: 8562712 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.7184. Min Act: -0.1700
Data Index: 1351646 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.7184. Min Act: -0.1700
Data Index: 1895259 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.7184. Min Act: -0.1700
Data Index: 1978596 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.6871. Min Act: -0.1700
Data Index: 5021793 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.6871. Min Act: -0.1700
Data Index: 8256176 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4371. Min Range: -6.4371
Max Act: 5.6871. Min Act: -0.1700
Data Index: 1223589 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19