Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1650 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1827. Min Range: -5.1827
Max Act: 5.1827. Min Act: -0.1700
Data Index: 2711868 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1827. Min Range: -5.1827
Max Act: 5.0889. Min Act: -0.1700
Data Index: 8422291 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1827. Min Range: -5.1827
Max Act: 5.0577. Min Act: -0.1700
Data Index: 2838941 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1827. Min Range: -5.1827
Max Act: 5.0577. Min Act: -0.1700
Data Index: 7215624 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.9952. Min Act: -0.1700
Data Index: 2038270 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.9327. Min Act: -0.1700
Data Index: 3008324 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.9639. Min Act: -0.1700
Data Index: 5411830 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.9639. Min Act: -0.1700
Data Index: 4661887 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.8702. Min Act: -0.1700
Data Index: 3045754 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.8702. Min Act: -0.1700
Data Index: 7315393 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.8702. Min Act: -0.1700
Data Index: 2495059 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.8389. Min Act: -0.1700
Data Index: 5110330 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.8389. Min Act: -0.1700
Data Index: 5058099 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.8077. Min Act: -0.1700
Data Index: 7264597 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.8077. Min Act: -0.1700
Data Index: 6595249 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.7764. Min Act: -0.1700
Data Index: 6075790 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.7764. Min Act: -0.1700
Data Index: 4434758 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.7764. Min Act: -0.1700
Data Index: 6109676 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.7764. Min Act: -0.1700
Data Index: 7689418 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.7764. Min Act: -0.1700
Data Index: 6123019 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19