Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.4508. Min Act: -0.1700
Data Index: 5863165 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.4196. Min Act: -0.1700
Data Index: 307458 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.3571. Min Act: -0.1700
Data Index: 861508 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.2946. Min Act: -0.1700
Data Index: 223963 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.2633. Min Act: -0.1700
Data Index: 8628096 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.2633. Min Act: -0.1700
Data Index: 2588715 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.2633. Min Act: -0.1700
Data Index: 2979322 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.1696. Min Act: -0.1700
Data Index: 2979323 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.2008. Min Act: -0.1700
Data Index: 2738897 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.1696. Min Act: -0.1700
Data Index: 6899182 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.1696. Min Act: -0.1700
Data Index: 1723311 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.1383. Min Act: -0.1700
Data Index: 5749004 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.1071. Min Act: -0.1700
Data Index: 107917 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.1071. Min Act: -0.1700
Data Index: 5708078 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.0758. Min Act: -0.1700
Data Index: 2274792 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.0758. Min Act: -0.1700
Data Index: 4501254 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.0758. Min Act: -0.1700
Data Index: 6908525 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.0758. Min Act: -0.1700
Data Index: 6375948 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.0133. Min Act: -0.1700
Data Index: 3950618 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.0446. Min Act: -0.1700
Data Index: 4494046 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19