Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1045. Min Range: -2.1045
Max Act: 2.1045. Min Act: -0.1698
Data Index: 8441684 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1045. Min Range: -2.1045
Max Act: 2.0374. Min Act: -0.1700
Data Index: 6767898 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1045. Min Range: -2.1045
Max Act: 2.0036. Min Act: -0.1700
Data Index: 2101873 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1045. Min Range: -2.1045
Max Act: 2.0036. Min Act: -0.1700
Data Index: 4156419 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9867. Min Act: -0.1700
Data Index: 192658 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9698. Min Act: -0.1700
Data Index: 5436596 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9698. Min Act: -0.1700
Data Index: 7167236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9528. Min Act: -0.1700
Data Index: 4596274 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9528. Min Act: -0.1700
Data Index: 3732708 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9528. Min Act: -0.1700
Data Index: 8682442 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9528. Min Act: -0.1700
Data Index: 6767897 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9528. Min Act: -0.1700
Data Index: 8673466 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9528. Min Act: -0.1700
Data Index: 5294446 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9698. Min Act: -0.1700
Data Index: 5492401 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9698. Min Act: -0.1700
Data Index: 2306619 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9698. Min Act: -0.1700
Data Index: 8575193 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9359. Min Act: -0.1700
Data Index: 1972995 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9528. Min Act: -0.1700
Data Index: 8708586 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9359. Min Act: -0.1700
Data Index: 7758284 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1045. Min Range: -2.1045
Max Act: 1.9188. Min Act: -0.1699
Data Index: 2406009 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19