Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1917. Min Range: -9.1917
Max Act: 9.1917. Min Act: -0.1700
Data Index: 3541635 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1917. Min Range: -9.1917
Max Act: 9.1292. Min Act: -0.1700
Data Index: 8214371 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1917. Min Range: -9.1917
Max Act: 9.0667. Min Act: -0.1700
Data Index: 4244153 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.8792. Min Act: -0.1700
Data Index: 2039880 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.8792. Min Act: -0.1700
Data Index: 1076275 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.8792. Min Act: -0.1700
Data Index: 2389889 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5042. Min Act: -0.1700
Data Index: 3471400 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5667. Min Act: -0.1700
Data Index: 6015755 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5667. Min Act: -0.1700
Data Index: 6434486 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 7951202 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5042. Min Act: -0.1700
Data Index: 8688023 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.5042. Min Act: -0.1700
Data Index: 6645184 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 8330820 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 154960 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 2932968 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.3792. Min Act: -0.1700
Data Index: 6722399 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 3984998 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 5903607 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.4417. Min Act: -0.1700
Data Index: 5941165 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1917. Min Range: -9.1917
Max Act: 8.3792. Min Act: -0.1700
Data Index: 3769245 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19