Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.7772. Min Act: -0.1700
Data Index: 8387320 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.7459. Min Act: -0.1700
Data Index: 8805528 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.6990. Min Act: -0.1700
Data Index: 8550404 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.5895. Min Act: -0.1700
Data Index: 5800327 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.6051. Min Act: -0.1700
Data Index: 3082339 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.5738. Min Act: -0.1700
Data Index: 4766873 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.5738. Min Act: -0.1700
Data Index: 2401354 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.5425. Min Act: -0.1700
Data Index: 7277201 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.5582. Min Act: -0.1700
Data Index: 5011413 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.5112. Min Act: -0.1700
Data Index: 292418 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.5112. Min Act: -0.1700
Data Index: 3075048 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.5112. Min Act: -0.1700
Data Index: 1315641 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.4799. Min Act: -0.1700
Data Index: 2075543 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.4955. Min Act: -0.1700
Data Index: 8048471 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.4642. Min Act: -0.1700
Data Index: 8121446 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.4642. Min Act: -0.1700
Data Index: 5238255 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.4328. Min Act: -0.1700
Data Index: 7210681 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.4485. Min Act: -0.1700
Data Index: 2692281 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.4485. Min Act: -0.1700
Data Index: 2536875 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7772. Min Range: -3.7772
Max Act: 3.4485. Min Act: -0.1700
Data Index: 7991046 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19