Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.9583. Min Act: -0.1700
Data Index: 7863595 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.9583. Min Act: -0.1700
Data Index: 7863594 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.8958. Min Act: -0.1700
Data Index: 4188108 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.8645. Min Act: -0.1700
Data Index: 1146924 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.8020. Min Act: -0.1700
Data Index: 6839835 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.7395. Min Act: -0.1700
Data Index: 20051 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.7708. Min Act: -0.1700
Data Index: 7486903 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.7395. Min Act: -0.1700
Data Index: 2871570 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.7083. Min Act: -0.1700
Data Index: 4097167 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.7395. Min Act: -0.1700
Data Index: 8691452 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.6770. Min Act: -0.1700
Data Index: 3690180 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.7083. Min Act: -0.1700
Data Index: 3315744 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.6458. Min Act: -0.1700
Data Index: 380330 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.6458. Min Act: -0.1700
Data Index: 2063315 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.6458. Min Act: -0.1700
Data Index: 4083411 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.6458. Min Act: -0.1700
Data Index: 6005831 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.5833. Min Act: -0.1700
Data Index: 4379042 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.5833. Min Act: -0.1700
Data Index: 1861954 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.5520. Min Act: -0.1700
Data Index: 7606119 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9583. Min Range: -5.9583
Max Act: 5.5833. Min Act: -0.1700
Data Index: 806422 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19