Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 1298532 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 3189408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 7485978 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 4118437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 7360023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 8049421 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 5595947 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 3262505 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 941984 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3577. Min Act: -0.1700
Data Index: 3363542 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2792. Min Act: -0.1700
Data Index: 3470850 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.3106. Min Act: -0.1700
Data Index: 2048316 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2478. Min Act: -0.1700
Data Index: 8808464 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2635. Min Act: -0.1700
Data Index: 807848 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2321. Min Act: -0.1700
Data Index: 5370840 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2321. Min Act: -0.1700
Data Index: 4314060 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2478. Min Act: -0.1700
Data Index: 6568620 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2321. Min Act: -0.1700
Data Index: 3308610 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2321. Min Act: -0.1700
Data Index: 5521641 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3577. Min Range: -3.3577
Max Act: 3.2321. Min Act: -0.1700
Data Index: 8153990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19