Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3723 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.4748. Min Act: -0.1700
Data Index: 1398812 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.4123. Min Act: -0.1700
Data Index: 6100704 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.4123. Min Act: -0.1700
Data Index: 6296273 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.2248. Min Act: -0.1700
Data Index: 159618 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.2248. Min Act: -0.1700
Data Index: 4466602 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.1623. Min Act: -0.1700
Data Index: 397550 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.0998. Min Act: -0.1700
Data Index: 8458435 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.0998. Min Act: -0.1700
Data Index: 6486131 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.0998. Min Act: -0.1700
Data Index: 3561815 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.0998. Min Act: -0.1700
Data Index: 3203004 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.0998. Min Act: -0.1700
Data Index: 3091175 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4748. Min Range: -11.4748
Max Act: 11.0998. Min Act: -0.1700
Data Index: 2803027 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4748. Min Range: -11.4748
Max Act: 10.9748. Min Act: -0.1700
Data Index: 6892801 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4748. Min Range: -11.4748
Max Act: 10.9123. Min Act: -0.1700
Data Index: 7546451 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4748. Min Range: -11.4748
Max Act: 10.9123. Min Act: -0.1700
Data Index: 2454768 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4748. Min Range: -11.4748
Max Act: 10.9123. Min Act: -0.1700
Data Index: 6540870 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4748. Min Range: -11.4748
Max Act: 10.9123. Min Act: -0.1700
Data Index: 2149903 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4748. Min Range: -11.4748
Max Act: 10.8498. Min Act: -0.1700
Data Index: 4932044 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4748. Min Range: -11.4748
Max Act: 10.8498. Min Act: -0.1700
Data Index: 7041777 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4748. Min Range: -11.4748
Max Act: 10.9123. Min Act: -0.1700
Data Index: 4795518 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19