Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3569. Min Range: -6.3569
Max Act: 6.3569. Min Act: -0.1700
Data Index: 8192738 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3569. Min Range: -6.3569
Max Act: 6.2944. Min Act: -0.1700
Data Index: 6011289 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3569. Min Range: -6.3569
Max Act: 6.2631. Min Act: -0.1700
Data Index: 3468573 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3569. Min Range: -6.3569
Max Act: 6.0756. Min Act: -0.1700
Data Index: 3944228 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3569. Min Range: -6.3569
Max Act: 6.0444. Min Act: -0.1700
Data Index: 3222651 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3569. Min Range: -6.3569
Max Act: 6.0444. Min Act: -0.1700
Data Index: 4322649 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3569. Min Range: -6.3569
Max Act: 6.0444. Min Act: -0.1700
Data Index: 5816565 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3569. Min Range: -6.3569
Max Act: 6.0131. Min Act: -0.1700
Data Index: 3753901 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.9819. Min Act: -0.1700
Data Index: 2208763 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.9506. Min Act: -0.1700
Data Index: 5765410 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.9506. Min Act: -0.1700
Data Index: 4235893 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.9194. Min Act: -0.1700
Data Index: 1450729 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.9194. Min Act: -0.1700
Data Index: 8495003 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.9194. Min Act: -0.1700
Data Index: 7039660 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.8881. Min Act: -0.1700
Data Index: 4433889 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.8881. Min Act: -0.1700
Data Index: 1909897 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.8881. Min Act: -0.1700
Data Index: 4760653 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.8881. Min Act: -0.1700
Data Index: 733839 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.8881. Min Act: -0.1700
Data Index: 6201043 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3569. Min Range: -6.3569
Max Act: 5.8569. Min Act: -0.1700
Data Index: 5572889 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19