Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2714. Min Range: -9.2714
Max Act: 9.2714. Min Act: -0.1700
Data Index: 5921105 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2714. Min Range: -9.2714
Max Act: 9.2089. Min Act: -0.1700
Data Index: 8188366 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2714. Min Range: -9.2714
Max Act: 9.1464. Min Act: -0.1700
Data Index: 561954 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2714. Min Range: -9.2714
Max Act: 9.1464. Min Act: -0.1700
Data Index: 5205568 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2714. Min Range: -9.2714
Max Act: 9.0839. Min Act: -0.1700
Data Index: 1926623 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2714. Min Range: -9.2714
Max Act: 9.0214. Min Act: -0.1700
Data Index: 6117884 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2714. Min Range: -9.2714
Max Act: 9.0214. Min Act: -0.1700
Data Index: 1403004 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.9589. Min Act: -0.1700
Data Index: 4450864 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2714. Min Range: -9.2714
Max Act: 9.0214. Min Act: -0.1700
Data Index: 2573979 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.8964. Min Act: -0.1700
Data Index: 1334896 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.8964. Min Act: -0.1700
Data Index: 3076640 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.8339. Min Act: -0.1700
Data Index: 338330 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.8339. Min Act: -0.1700
Data Index: 1310997 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.8339. Min Act: -0.1700
Data Index: 6431272 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.7714. Min Act: -0.1700
Data Index: 2321411 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.7714. Min Act: -0.1700
Data Index: 5983808 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.7714. Min Act: -0.1700
Data Index: 4881477 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.7714. Min Act: -0.1700
Data Index: 2428163 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.7089. Min Act: -0.1700
Data Index: 3074409 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2714. Min Range: -9.2714
Max Act: 8.7714. Min Act: -0.1700
Data Index: 3263544 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19