Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3765 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4484. Min Range: -8.4484
Max Act: 8.4484. Min Act: -0.1700
Data Index: 5129133 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4484. Min Range: -8.4484
Max Act: 8.3234. Min Act: -0.1700
Data Index: 2600482 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4484. Min Range: -8.4484
Max Act: 8.1984. Min Act: -0.1700
Data Index: 2849655 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4484. Min Range: -8.4484
Max Act: 8.1359. Min Act: -0.1700
Data Index: 6849603 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4484. Min Range: -8.4484
Max Act: 8.0422. Min Act: -0.1700
Data Index: 1185721 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4484. Min Range: -8.4484
Max Act: 8.0109. Min Act: -0.1700
Data Index: 7090014 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.9484. Min Act: -0.1700
Data Index: 7234236 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.8859. Min Act: -0.1700
Data Index: 6817271 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.8859. Min Act: -0.1700
Data Index: 5304411 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.8547. Min Act: -0.1700
Data Index: 798324 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.8234. Min Act: -0.1700
Data Index: 382398 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.8234. Min Act: -0.1700
Data Index: 6494491 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.8234. Min Act: -0.1700
Data Index: 7370519 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.7922. Min Act: -0.1700
Data Index: 564377 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.7609. Min Act: -0.1700
Data Index: 2388257 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.7609. Min Act: -0.1700
Data Index: 3886043 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.7609. Min Act: -0.1700
Data Index: 7650262 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.7609. Min Act: -0.1700
Data Index: 1833588 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.6984. Min Act: -0.1700
Data Index: 4803049 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4484. Min Range: -8.4484
Max Act: 7.6672. Min Act: -0.1700
Data Index: 2136768 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19