Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5662 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4605. Min Range: -5.4605
Max Act: 5.4605. Min Act: -0.1700
Data Index: 4835857 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4605. Min Range: -5.4605
Max Act: 5.4605. Min Act: -0.1700
Data Index: 3158628 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4605. Min Range: -5.4605
Max Act: 5.2730. Min Act: -0.1700
Data Index: 937697 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4605. Min Range: -5.4605
Max Act: 5.1480. Min Act: -0.1700
Data Index: 3140045 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4605. Min Range: -5.4605
Max Act: 5.1167. Min Act: -0.1700
Data Index: 1250874 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4605. Min Range: -5.4605
Max Act: 5.0855. Min Act: -0.1700
Data Index: 3899205 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4605. Min Range: -5.4605
Max Act: 5.0542. Min Act: -0.1700
Data Index: 1333408 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9917. Min Act: -0.1700
Data Index: 460488 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9917. Min Act: -0.1700
Data Index: 5214770 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9917. Min Act: -0.1700
Data Index: 3399088 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9605. Min Act: -0.1700
Data Index: 3231123 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9605. Min Act: -0.1700
Data Index: 8193490 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9605. Min Act: -0.1700
Data Index: 6013417 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9292. Min Act: -0.1700
Data Index: 5219651 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9292. Min Act: -0.1700
Data Index: 6393696 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9292. Min Act: -0.1700
Data Index: 2062483 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.8980. Min Act: -0.1700
Data Index: 823252 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.8980. Min Act: -0.1700
Data Index: 1804470 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.8980. Min Act: -0.1700
Data Index: 5124872 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4605. Min Range: -5.4605
Max Act: 4.9292. Min Act: -0.1700
Data Index: 3140038 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19