Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4810 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.8181. Min Act: -0.1700
Data Index: 1964438 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.5991. Min Act: -0.1700
Data Index: 7488092 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.5365. Min Act: -0.1700
Data Index: 97736 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.4739. Min Act: -0.1700
Data Index: 6175141 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.4269. Min Act: -0.1700
Data Index: 315766 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.4582. Min Act: -0.1700
Data Index: 5359810 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.4269. Min Act: -0.1700
Data Index: 8120331 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.4425. Min Act: -0.1700
Data Index: 1579511 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.3955. Min Act: -0.1700
Data Index: 4464075 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.3955. Min Act: -0.1700
Data Index: 4475311 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.4112. Min Act: -0.1700
Data Index: 3436578 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.4112. Min Act: -0.1700
Data Index: 5051914 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.4112. Min Act: -0.1700
Data Index: 3346270 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.3798. Min Act: -0.1700
Data Index: 6752078 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.3955. Min Act: -0.1700
Data Index: 3293209 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.3798. Min Act: -0.1700
Data Index: 8784459 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.3955. Min Act: -0.1700
Data Index: 2592074 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.3955. Min Act: -0.1700
Data Index: 4917436 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.3641. Min Act: -0.1700
Data Index: 1482789 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8181. Min Range: -3.8181
Max Act: 3.3641. Min Act: -0.1700
Data Index: 7567550 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19