Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1118 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4558. Min Range: -5.4558
Max Act: 5.4558. Min Act: -0.1700
Data Index: 6953607 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4558. Min Range: -5.4558
Max Act: 5.1433. Min Act: -0.1700
Data Index: 3348487 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4558. Min Range: -5.4558
Max Act: 5.1433. Min Act: -0.1700
Data Index: 1440376 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4558. Min Range: -5.4558
Max Act: 5.1745. Min Act: -0.1700
Data Index: 3413996 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4558. Min Range: -5.4558
Max Act: 5.0495. Min Act: -0.1700
Data Index: 1990782 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.8933. Min Act: -0.1700
Data Index: 8368727 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.9245. Min Act: -0.1700
Data Index: 3012006 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.9245. Min Act: -0.1700
Data Index: 3652068 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.8620. Min Act: -0.1700
Data Index: 8158038 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.8620. Min Act: -0.1700
Data Index: 5121037 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.8308. Min Act: -0.1700
Data Index: 7229022 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.8308. Min Act: -0.1700
Data Index: 455972 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.8308. Min Act: -0.1700
Data Index: 5330235 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.7683. Min Act: -0.1700
Data Index: 3156890 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.8308. Min Act: -0.1700
Data Index: 895823 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.7683. Min Act: -0.1700
Data Index: 1232900 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.7995. Min Act: -0.1700
Data Index: 4203707 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.7995. Min Act: -0.1700
Data Index: 5596384 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.7370. Min Act: -0.1700
Data Index: 8343336 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4558. Min Range: -5.4558
Max Act: 4.7683. Min Act: -0.1700
Data Index: 5079025 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19