Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0578. Min Range: -2.0578
Max Act: 2.0578. Min Act: -0.1700
Data Index: 5017623 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0578. Min Range: -2.0578
Max Act: 2.0241. Min Act: -0.1700
Data Index: 2383045 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0578. Min Range: -2.0578
Max Act: 2.0241. Min Act: -0.1700
Data Index: 4444909 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9903. Min Act: -0.1700
Data Index: 2769222 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0578. Min Range: -2.0578
Max Act: 2.0241. Min Act: -0.1700
Data Index: 2656071 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9734. Min Act: -0.1700
Data Index: 3124543 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9565. Min Act: -0.1700
Data Index: 7408348 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9734. Min Act: -0.1700
Data Index: 7229694 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9734. Min Act: -0.1700
Data Index: 5677432 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9565. Min Act: -0.1700
Data Index: 3998903 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9734. Min Act: -0.1700
Data Index: 603273 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9565. Min Act: -0.1700
Data Index: 4238976 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9565. Min Act: -0.1700
Data Index: 2590891 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9565. Min Act: -0.1700
Data Index: 6807530 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9565. Min Act: -0.1700
Data Index: 2451274 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9565. Min Act: -0.1700
Data Index: 7037786 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9565. Min Act: -0.1700
Data Index: 51787 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9395. Min Act: -0.1700
Data Index: 708648 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9734. Min Act: -0.1700
Data Index: 4916141 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0578. Min Range: -2.0578
Max Act: 1.9565. Min Act: -0.1700
Data Index: 2357730 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19