Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1345 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2128. Min Range: -5.2128
Max Act: 5.2128. Min Act: -0.1700
Data Index: 7167562 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2128. Min Range: -5.2128
Max Act: 5.0565. Min Act: -0.1700
Data Index: 8694455 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2128. Min Range: -5.2128
Max Act: 5.0565. Min Act: -0.1700
Data Index: 5048358 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.9628. Min Act: -0.1700
Data Index: 751808 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.9940. Min Act: -0.1700
Data Index: 3962369 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.9940. Min Act: -0.1700
Data Index: 8078050 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.9315. Min Act: -0.1700
Data Index: 3965967 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.9003. Min Act: -0.1700
Data Index: 7320591 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.9003. Min Act: -0.1700
Data Index: 1201396 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8690. Min Act: -0.1700
Data Index: 8694457 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.9003. Min Act: -0.1700
Data Index: 784677 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8690. Min Act: -0.1700
Data Index: 7930844 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8690. Min Act: -0.1700
Data Index: 4790049 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8378. Min Act: -0.1700
Data Index: 3112531 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8065. Min Act: -0.1700
Data Index: 8694451 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8378. Min Act: -0.1700
Data Index: 551662 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8378. Min Act: -0.1700
Data Index: 4077057 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8065. Min Act: -0.1700
Data Index: 6384399 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7753. Min Act: -0.1700
Data Index: 2874781 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8065. Min Act: -0.1700
Data Index: 8510898 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19