Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5313 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0636. Min Range: -8.0636
Max Act: 8.0636. Min Act: -0.1700
Data Index: 1496656 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0636. Min Range: -8.0636
Max Act: 8.0011. Min Act: -0.1700
Data Index: 104674 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0636. Min Range: -8.0636
Max Act: 8.0011. Min Act: -0.1700
Data Index: 1493985 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.9386. Min Act: -0.1700
Data Index: 8457664 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.9386. Min Act: -0.1699
Data Index: 1542984 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.9386. Min Act: -0.1700
Data Index: 5904916 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.8761. Min Act: -0.1700
Data Index: 1073646 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.8761. Min Act: -0.1700
Data Index: 5400190 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.8136. Min Act: -0.1700
Data Index: 6613534 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.8136. Min Act: -0.1700
Data Index: 3078326 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.8136. Min Act: -0.1700
Data Index: 7850653 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.7511. Min Act: -0.1700
Data Index: 2058926 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.7511. Min Act: -0.1700
Data Index: 7486934 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.6886. Min Act: -0.1700
Data Index: 2908856 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.7511. Min Act: -0.1700
Data Index: 981677 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.7511. Min Act: -0.1700
Data Index: 7610722 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.6886. Min Act: -0.1700
Data Index: 8172810 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.6261. Min Act: -0.1700
Data Index: 4386367 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.6261. Min Act: -0.1700
Data Index: 6243799 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0636. Min Range: -8.0636
Max Act: 7.6261. Min Act: -0.1700
Data Index: 6260024 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19