Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2504 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.4424. Min Act: -0.1700
Data Index: 5242101 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.3799. Min Act: -0.1700
Data Index: 5242100 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.3799. Min Act: -0.1700
Data Index: 3305186 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.2862. Min Act: -0.1700
Data Index: 4731884 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.2862. Min Act: -0.1700
Data Index: 5134503 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.2862. Min Act: -0.1700
Data Index: 7851067 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.2237. Min Act: -0.1700
Data Index: 109636 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.1924. Min Act: -0.1700
Data Index: 1578675 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.1924. Min Act: -0.1700
Data Index: 1356033 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.1612. Min Act: -0.1700
Data Index: 6983867 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.1299. Min Act: -0.1700
Data Index: 957200 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.0987. Min Act: -0.1700
Data Index: 6797716 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.0674. Min Act: -0.1700
Data Index: 3347511 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.0362. Min Act: -0.1700
Data Index: 7930268 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.0362. Min Act: -0.1700
Data Index: 2061760 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4424. Min Range: -7.4424
Max Act: 7.0362. Min Act: -0.1700
Data Index: 3938347 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4424. Min Range: -7.4424
Max Act: 6.9424. Min Act: -0.1700
Data Index: 6459754 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4424. Min Range: -7.4424
Max Act: 6.9424. Min Act: -0.1700
Data Index: 8513642 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4424. Min Range: -7.4424
Max Act: 6.9424. Min Act: -0.1700
Data Index: 1204438 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4424. Min Range: -7.4424
Max Act: 6.9424. Min Act: -0.1700
Data Index: 7749551 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19