Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4298 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.7514. Min Act: -0.1700
Data Index: 290884 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.6577. Min Act: -0.1700
Data Index: 459879 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.6889. Min Act: -0.1700
Data Index: 2747528 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.5952. Min Act: -0.1700
Data Index: 4775084 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.6264. Min Act: -0.1700
Data Index: 290879 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.5639. Min Act: -0.1700
Data Index: 1023635 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.5639. Min Act: -0.1700
Data Index: 3355835 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.5639. Min Act: -0.1700
Data Index: 290883 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.5327. Min Act: -0.1700
Data Index: 290886 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.5327. Min Act: -0.1700
Data Index: 2293808 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.5327. Min Act: -0.1700
Data Index: 1355047 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.5014. Min Act: -0.1700
Data Index: 290887 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.4702. Min Act: -0.1700
Data Index: 7306400 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.4702. Min Act: -0.1700
Data Index: 498723 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.4389. Min Act: -0.1700
Data Index: 498727 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.4077. Min Act: -0.1700
Data Index: 290873 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.4077. Min Act: -0.1700
Data Index: 5823726 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.3764. Min Act: -0.1700
Data Index: 4151600 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.3764. Min Act: -0.1700
Data Index: 3989292 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7514. Min Range: -5.7514
Max Act: 5.3764. Min Act: -0.1700
Data Index: 290874 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19