Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 290 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.4508. Min Act: -0.1700
Data Index: 4226409 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.2320. Min Act: -0.1700
Data Index: 626516 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.9820. Min Act: -0.1700
Data Index: 5375260 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4508. Min Range: -5.4508
Max Act: 5.0133. Min Act: -0.1700
Data Index: 1568231 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.9508. Min Act: -0.1700
Data Index: 3336001 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.9195. Min Act: -0.1700
Data Index: 1075855 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.9195. Min Act: -0.1700
Data Index: 8492535 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.9508. Min Act: -0.1700
Data Index: 1714472 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.9195. Min Act: -0.1700
Data Index: 8169651 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.8570. Min Act: -0.1700
Data Index: 5848242 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.8258. Min Act: -0.1700
Data Index: 1860234 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.8258. Min Act: -0.1700
Data Index: 2846951 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.8258. Min Act: -0.1700
Data Index: 1018486 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.8258. Min Act: -0.1700
Data Index: 5927951 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.7945. Min Act: -0.1700
Data Index: 6820664 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.7633. Min Act: -0.1700
Data Index: 2871844 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.7945. Min Act: -0.1700
Data Index: 5231987 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.7945. Min Act: -0.1700
Data Index: 3589111 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.7945. Min Act: -0.1700
Data Index: 131334 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4508. Min Range: -5.4508
Max Act: 4.7945. Min Act: -0.1700
Data Index: 3691501 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19