Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1500. Min Range: -7.1500
Max Act: 7.1500. Min Act: -0.1700
Data Index: 3317258 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.7125. Min Act: -0.1700
Data Index: 1185901 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.6500. Min Act: -0.1700
Data Index: 2011540 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.5563. Min Act: -0.1700
Data Index: 1801315 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.4938. Min Act: -0.1700
Data Index: 6674771 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.4313. Min Act: -0.1700
Data Index: 2144759 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.3688. Min Act: -0.1700
Data Index: 4062364 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.3063. Min Act: -0.1700
Data Index: 2397022 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.2750. Min Act: -0.1700
Data Index: 2652208 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.2750. Min Act: -0.1700
Data Index: 4805730 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.2438. Min Act: -0.1700
Data Index: 1822104 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.2438. Min Act: -0.1700
Data Index: 3435509 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.2438. Min Act: -0.1700
Data Index: 7547343 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.2125. Min Act: -0.1700
Data Index: 232361 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.2438. Min Act: -0.1700
Data Index: 6665106 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.2125. Min Act: -0.1700
Data Index: 3838978 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.1813. Min Act: -0.1700
Data Index: 2234135 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.1813. Min Act: -0.1700
Data Index: 781119 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.1500. Min Act: -0.1700
Data Index: 3255712 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1500. Min Range: -7.1500
Max Act: 6.1813. Min Act: -0.1700
Data Index: 8037157 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19