Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1419 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0749. Min Act: -0.1700
Data Index: 3558393 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0749. Min Act: -0.1700
Data Index: 4814392 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0436. Min Act: -0.1700
Data Index: 2807793 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0123. Min Act: -0.1700
Data Index: 4703815 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0436. Min Act: -0.1700
Data Index: 874832 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0436. Min Act: -0.1700
Data Index: 8193647 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0436. Min Act: -0.1700
Data Index: 7060658 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0749. Min Range: -4.0749
Max Act: 3.9811. Min Act: -0.1700
Data Index: 4255183 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0123. Min Act: -0.1700
Data Index: 7182844 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0123. Min Act: -0.1700
Data Index: 4807199 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0123. Min Act: -0.1700
Data Index: 6906570 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0749. Min Range: -4.0749
Max Act: 4.0123. Min Act: -0.1700
Data Index: 7084495 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0749. Min Range: -4.0749
Max Act: 3.9811. Min Act: -0.1700
Data Index: 6767473 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0749. Min Range: -4.0749
Max Act: 3.9811. Min Act: -0.1700
Data Index: 3119793 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0749. Min Range: -4.0749
Max Act: 3.9811. Min Act: -0.1700
Data Index: 4939098 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0749. Min Range: -4.0749
Max Act: 3.9498. Min Act: -0.1700
Data Index: 7321727 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0749. Min Range: -4.0749
Max Act: 3.9811. Min Act: -0.1700
Data Index: 6700020 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0749. Min Range: -4.0749
Max Act: 3.9811. Min Act: -0.1700
Data Index: 4593187 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0749. Min Range: -4.0749
Max Act: 3.9811. Min Act: -0.1700
Data Index: 1154678 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0749. Min Range: -4.0749
Max Act: 3.9811. Min Act: -0.1700
Data Index: 6140246 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19