Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.8487. Min Act: -0.1700
Data Index: 5235575 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.8174. Min Act: -0.1700
Data Index: 7341698 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.8174. Min Act: -0.1700
Data Index: 1495590 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.7862. Min Act: -0.1700
Data Index: 624747 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.7549. Min Act: -0.1700
Data Index: 581946 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.7237. Min Act: -0.1700
Data Index: 3520914 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.7549. Min Act: -0.1700
Data Index: 1320333 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.7549. Min Act: -0.1700
Data Index: 8439890 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.7237. Min Act: -0.1699
Data Index: 591462 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.7237. Min Act: -0.1700
Data Index: 2708404 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.6924. Min Act: -0.1700
Data Index: 6570958 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.7549. Min Act: -0.1700
Data Index: 1016292 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.7237. Min Act: -0.1700
Data Index: 8191715 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.6924. Min Act: -0.1700
Data Index: 7456059 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.6924. Min Act: -0.1700
Data Index: 3014123 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.6924. Min Act: -0.1700
Data Index: 3039344 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.6612. Min Act: -0.1700
Data Index: 1192216 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.6924. Min Act: -0.1700
Data Index: 3307633 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.6612. Min Act: -0.1700
Data Index: 6309883 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8487. Min Range: -6.8487
Max Act: 6.6612. Min Act: -0.1700
Data Index: 425009 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19