Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1920 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.9069. Min Act: -0.1700
Data Index: 6520581 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.9069. Min Act: -0.1700
Data Index: 6285287 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.8131. Min Act: -0.1700
Data Index: 4202778 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.8444. Min Act: -0.1700
Data Index: 5507284 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.8444. Min Act: -0.1700
Data Index: 3896909 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.8131. Min Act: -0.1700
Data Index: 3690675 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.7506. Min Act: -0.1700
Data Index: 730586 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.7506. Min Act: -0.1700
Data Index: 425964 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.7506. Min Act: -0.1700
Data Index: 2117120 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.6881. Min Act: -0.1700
Data Index: 2625830 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.6569. Min Act: -0.1700
Data Index: 8651941 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.6881. Min Act: -0.1700
Data Index: 2427330 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.6256. Min Act: -0.1700
Data Index: 3846744 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.6256. Min Act: -0.1700
Data Index: 6943659 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.5944. Min Act: -0.1700
Data Index: 7944764 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.5944. Min Act: -0.1700
Data Index: 8825475 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.5631. Min Act: -0.1700
Data Index: 2549619 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.5631. Min Act: -0.1700
Data Index: 2001120 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.5631. Min Act: -0.1700
Data Index: 8431433 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9069. Min Range: -5.9069
Max Act: 5.5631. Min Act: -0.1700
Data Index: 8430522 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19