Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.2667. Min Act: -0.1688
Data Index: 3857598 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.2355. Min Act: -0.1686
Data Index: 8193301 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.2042. Min Act: -0.1698
Data Index: 5630033 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.1105. Min Act: -0.0511
Data Index: 6613488 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.1105. Min Act: -0.1697
Data Index: 6613487 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.1105. Min Act: -0.1696
Data Index: 5548579 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.0792. Min Act: -0.1695
Data Index: 8350016 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.0792. Min Act: -0.1700
Data Index: 1552403 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.0480. Min Act: -0.1680
Data Index: 4936707 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2667. Min Range: -6.2667
Max Act: 6.0167. Min Act: -0.1700
Data Index: 7046242 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.9855. Min Act: -0.0511
Data Index: 8193309 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.9230. Min Act: -0.1011
Data Index: 7195436 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.9230. Min Act: -0.1700
Data Index: 2988385 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.9230. Min Act: -0.1564
Data Index: 8744932 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.9230. Min Act: -0.1694
Data Index: 6613489 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.9230. Min Act: -0.1697
Data Index: 6287500 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.8917. Min Act: -0.1196
Data Index: 6738889 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.8605. Min Act: -0.1700
Data Index: 7305743 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.8292. Min Act: -0.1700
Data Index: 2275978 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2667. Min Range: -6.2667
Max Act: 5.8605. Min Act: -0.1700
Data Index: 1476742 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19