Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0487. Min Range: -6.0487
Max Act: 6.0487. Min Act: -0.1700
Data Index: 3008936 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.8300. Min Act: -0.1700
Data Index: 2014144 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.7675. Min Act: -0.1700
Data Index: 6940150 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.6737. Min Act: -0.1700
Data Index: 3174815 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.6737. Min Act: -0.1700
Data Index: 7442933 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.6737. Min Act: -0.1700
Data Index: 2790095 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.6425. Min Act: -0.1700
Data Index: 5971193 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.6112. Min Act: -0.1700
Data Index: 8065100 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.6112. Min Act: -0.1700
Data Index: 7379315 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5800. Min Act: -0.1700
Data Index: 6591759 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5800. Min Act: -0.1700
Data Index: 7831237 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5800. Min Act: -0.1700
Data Index: 3020932 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5800. Min Act: -0.1700
Data Index: 50619 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.6112. Min Act: -0.1700
Data Index: 1578382 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5800. Min Act: -0.1700
Data Index: 6740062 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5487. Min Act: -0.1700
Data Index: 3534879 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5487. Min Act: -0.1700
Data Index: 1495006 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5487. Min Act: -0.1700
Data Index: 4797628 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5487. Min Act: -0.1700
Data Index: 3252132 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0487. Min Range: -6.0487
Max Act: 5.5487. Min Act: -0.1700
Data Index: 1581877 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19