Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5802 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.6559. Min Act: -0.1700
Data Index: 5672566 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.6247. Min Act: -0.1700
Data Index: 6945060 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.4997. Min Act: -0.1700
Data Index: 2846615 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.4059. Min Act: -0.1700
Data Index: 6943945 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.4059. Min Act: -0.1700
Data Index: 2921631 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.3747. Min Act: -0.1700
Data Index: 5735206 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.3747. Min Act: -0.1700
Data Index: 4234026 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.3434. Min Act: -0.1700
Data Index: 8581660 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.3122. Min Act: -0.1700
Data Index: 5841821 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2809. Min Act: -0.1700
Data Index: 5564375 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2809. Min Act: -0.1700
Data Index: 487994 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2497. Min Act: -0.1700
Data Index: 5589145 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1872. Min Act: -0.1700
Data Index: 4378258 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1872. Min Act: -0.1700
Data Index: 2663843 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1872. Min Act: -0.1700
Data Index: 6934498 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1559. Min Act: -0.1700
Data Index: 1425466 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1559. Min Act: -0.1700
Data Index: 1148099 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1247. Min Act: -0.1700
Data Index: 358901 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0622. Min Act: -0.1700
Data Index: 6521468 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0622. Min Act: -0.1700
Data Index: 2879519 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19