Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1464. Min Range: -6.1464
Max Act: 6.1464. Min Act: -0.1700
Data Index: 5920419 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1464. Min Range: -6.1464
Max Act: 6.1464. Min Act: -0.1700
Data Index: 1110237 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1464. Min Range: -6.1464
Max Act: 6.1464. Min Act: -0.1700
Data Index: 2873165 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1464. Min Range: -6.1464
Max Act: 6.1151. Min Act: -0.1700
Data Index: 8173762 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1464. Min Range: -6.1464
Max Act: 6.0214. Min Act: -0.1700
Data Index: 3482201 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.9901. Min Act: -0.1700
Data Index: 5590208 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.9589. Min Act: -0.1700
Data Index: 9160 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.9589. Min Act: -0.1700
Data Index: 1185590 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.9276. Min Act: -0.1700
Data Index: 6932611 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.8651. Min Act: -0.1700
Data Index: 2041608 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.7714. Min Act: -0.1700
Data Index: 1256005 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.7401. Min Act: -0.1700
Data Index: 598683 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.7089. Min Act: -0.1700
Data Index: 3604531 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.7089. Min Act: -0.1700
Data Index: 5909738 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.6776. Min Act: -0.1700
Data Index: 3881483 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.6776. Min Act: -0.1700
Data Index: 1824880 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.6776. Min Act: -0.1700
Data Index: 2380397 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.6776. Min Act: -0.1700
Data Index: 188385 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.6776. Min Act: -0.1700
Data Index: 161644 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1464. Min Range: -6.1464
Max Act: 5.6464. Min Act: -0.1700
Data Index: 4878765 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19