Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1372 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1675. Min Range: -5.1675
Max Act: 5.1675. Min Act: -0.1700
Data Index: 7655552 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1675. Min Range: -5.1675
Max Act: 5.0737. Min Act: -0.1699
Data Index: 8740022 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.9800. Min Act: -0.1700
Data Index: 8438332 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1675. Min Range: -5.1675
Max Act: 5.0112. Min Act: -0.1700
Data Index: 3868610 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.9487. Min Act: -0.1700
Data Index: 6214481 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.9487. Min Act: -0.1700
Data Index: 6852708 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.9175. Min Act: -0.1700
Data Index: 7159477 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.9175. Min Act: -0.1700
Data Index: 3766231 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.9175. Min Act: -0.1700
Data Index: 3775208 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.9175. Min Act: -0.1699
Data Index: 6289250 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8862. Min Act: -0.1700
Data Index: 8959 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8862. Min Act: -0.1700
Data Index: 1837729 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8862. Min Act: -0.1700
Data Index: 1837733 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8862. Min Act: -0.1700
Data Index: 6796367 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8550. Min Act: -0.1700
Data Index: 4032912 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8862. Min Act: -0.1700
Data Index: 8274251 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8550. Min Act: -0.1700
Data Index: 8178302 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8550. Min Act: -0.1700
Data Index: 564010 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8550. Min Act: -0.1700
Data Index: 2740882 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1675. Min Range: -5.1675
Max Act: 4.8550. Min Act: -0.1700
Data Index: 4753711 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19