Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1525 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1632. Min Range: -4.1632
Max Act: 4.1632. Min Act: -0.1700
Data Index: 1710233 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1632. Min Range: -4.1632
Max Act: 4.1007. Min Act: -0.1700
Data Index: 2839978 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1632. Min Range: -4.1632
Max Act: 4.0382. Min Act: -0.1700
Data Index: 6117139 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.9756. Min Act: -0.1700
Data Index: 3211639 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.9131. Min Act: -0.1700
Data Index: 3355053 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.8818. Min Act: -0.1700
Data Index: 7499742 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.9131. Min Act: -0.1700
Data Index: 5066596 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.9131. Min Act: -0.1700
Data Index: 559759 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.9131. Min Act: -0.1700
Data Index: 4555412 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.8818. Min Act: -0.1700
Data Index: 7818397 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.9131. Min Act: -0.1700
Data Index: 2861875 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.8506. Min Act: -0.1700
Data Index: 211728 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.8506. Min Act: -0.1700
Data Index: 5522230 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.8193. Min Act: -0.1700
Data Index: 4551548 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.8193. Min Act: -0.1700
Data Index: 913835 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.8506. Min Act: -0.1700
Data Index: 5656978 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.7880. Min Act: -0.1700
Data Index: 774383 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.7880. Min Act: -0.1700
Data Index: 5036317 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.7880. Min Act: -0.1700
Data Index: 246357 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1632. Min Range: -4.1632
Max Act: 3.7880. Min Act: -0.1700
Data Index: 5949056 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19