Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0296. Min Range: -2.0296
Max Act: 2.0296. Min Act: -0.1700
Data Index: 5635357 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9789. Min Act: -0.1700
Data Index: 5635359 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9619. Min Act: -0.1700
Data Index: 8501844 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9450. Min Act: -0.1700
Data Index: 5091758 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9619. Min Act: -0.1700
Data Index: 4934080 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9619. Min Act: -0.1700
Data Index: 4338455 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9280. Min Act: -0.1700
Data Index: 1978573 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9450. Min Act: -0.1700
Data Index: 528815 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9280. Min Act: -0.1700
Data Index: 2643870 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9109. Min Act: -0.1700
Data Index: 2861461 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9109. Min Act: -0.1700
Data Index: 5911607 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9109. Min Act: -0.1700
Data Index: 267207 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.9109. Min Act: -0.1700
Data Index: 3442593 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.8939. Min Act: -0.1700
Data Index: 828476 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.8768. Min Act: -0.1700
Data Index: 3035143 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.8939. Min Act: -0.1700
Data Index: 1247658 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.8768. Min Act: -0.1700
Data Index: 3366761 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.8768. Min Act: -0.1700
Data Index: 3529396 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.8597. Min Act: -0.1700
Data Index: 6154229 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0296. Min Range: -2.0296
Max Act: 1.8768. Min Act: -0.1700
Data Index: 4780756 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19