Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3910 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.1608. Min Act: -0.1700
Data Index: 4999651 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.1293. Min Act: -0.1700
Data Index: 2266031 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0820. Min Act: -0.1700
Data Index: 3163912 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0978. Min Act: -0.1700
Data Index: 7286831 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0820. Min Act: -0.1700
Data Index: 7498892 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0662. Min Act: -0.1700
Data Index: 1824669 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0820. Min Act: -0.1699
Data Index: 5838648 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0978. Min Act: -0.1700
Data Index: 4385498 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0820. Min Act: -0.1700
Data Index: 4186069 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0662. Min Act: -0.1700
Data Index: 7504074 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0504. Min Act: -0.1700
Data Index: 1489155 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0978. Min Act: -0.1700
Data Index: 2617089 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0189. Min Act: -0.1700
Data Index: 5175415 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0504. Min Act: -0.1700
Data Index: 7265846 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0662. Min Act: -0.1700
Data Index: 449526 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0504. Min Act: -0.1700
Data Index: 6220023 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0504. Min Act: -0.1700
Data Index: 3892486 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0031. Min Act: -0.1700
Data Index: 5737857 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0347. Min Act: -0.1700
Data Index: 7270609 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1608. Min Range: -3.1608
Max Act: 3.0189. Min Act: -0.1700
Data Index: 7465898 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19