Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5511. Min Range: -10.5511
Max Act: 10.5511. Min Act: -0.1700
Data Index: 4426587 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5511. Min Range: -10.5511
Max Act: 10.3636. Min Act: -0.1700
Data Index: 7031864 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5511. Min Range: -10.5511
Max Act: 10.3636. Min Act: -0.1700
Data Index: 8361437 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5511. Min Range: -10.5511
Max Act: 10.2386. Min Act: -0.1700
Data Index: 6654288 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.9886. Min Act: -0.1700
Data Index: 5856056 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5511. Min Range: -10.5511
Max Act: 10.0511. Min Act: -0.1700
Data Index: 4455781 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.8636. Min Act: -0.1700
Data Index: 2080797 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.8011. Min Act: -0.1700
Data Index: 387207 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.8011. Min Act: -0.1700
Data Index: 4859762 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.7386. Min Act: -0.1700
Data Index: 7255564 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.7386. Min Act: -0.1700
Data Index: 4799181 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.7386. Min Act: -0.1700
Data Index: 6098689 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.6761. Min Act: -0.1700
Data Index: 3945999 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.6136. Min Act: -0.1700
Data Index: 7944651 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.6136. Min Act: -0.1700
Data Index: 5700424 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.6136. Min Act: -0.1700
Data Index: 6430240 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.6136. Min Act: -0.1700
Data Index: 413004 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.5511. Min Act: -0.1700
Data Index: 7607684 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.5511. Min Act: -0.1700
Data Index: 6279932 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5511. Min Range: -10.5511
Max Act: 9.4886. Min Act: -0.1700
Data Index: 2199647 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19