Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2131. Min Range: -5.2131
Max Act: 5.2131. Min Act: -0.1700
Data Index: 6655982 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2131. Min Range: -5.2131
Max Act: 5.0569. Min Act: -0.1700
Data Index: 4734231 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2131. Min Range: -5.2131
Max Act: 5.0569. Min Act: -0.1700
Data Index: 5698984 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2131. Min Range: -5.2131
Max Act: 5.0256. Min Act: -0.1700
Data Index: 2192545 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8694. Min Act: -0.1700
Data Index: 5118590 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8381. Min Act: -0.1700
Data Index: 6353203 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8069. Min Act: -0.1700
Data Index: 2665277 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8381. Min Act: -0.1700
Data Index: 5684524 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8381. Min Act: -0.1700
Data Index: 3778905 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8694. Min Act: -0.1700
Data Index: 7950671 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8069. Min Act: -0.1700
Data Index: 8291035 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8069. Min Act: -0.1700
Data Index: 895382 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8069. Min Act: -0.1700
Data Index: 4323490 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.8069. Min Act: -0.1700
Data Index: 3043811 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.7756. Min Act: -0.1700
Data Index: 6048834 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.7756. Min Act: -0.1700
Data Index: 7893888 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.7756. Min Act: -0.1700
Data Index: 3602681 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.7756. Min Act: -0.1700
Data Index: 5369514 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.7756. Min Act: -0.1700
Data Index: 6577422 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2131. Min Range: -5.2131
Max Act: 4.7444. Min Act: -0.1700
Data Index: 7310559 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19