Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.5261. Min Act: -0.1700
Data Index: 1844652 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.3698. Min Act: -0.1700
Data Index: 8481159 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.3698. Min Act: -0.1700
Data Index: 342004 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.3385. Min Act: -0.1700
Data Index: 8237137 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.3073. Min Act: -0.1700
Data Index: 505772 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.3073. Min Act: -0.1700
Data Index: 4971145 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.2448. Min Act: -0.1700
Data Index: 2483846 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.2135. Min Act: -0.1700
Data Index: 2436229 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.2135. Min Act: -0.1700
Data Index: 6993867 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.1823. Min Act: -0.1700
Data Index: 5797691 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.2135. Min Act: -0.1700
Data Index: 5219765 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.2448. Min Act: -0.1700
Data Index: 5363383 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.1510. Min Act: -0.1700
Data Index: 8727119 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.1823. Min Act: -0.1700
Data Index: 1832216 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.1823. Min Act: -0.1700
Data Index: 1397046 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.1510. Min Act: -0.1700
Data Index: 5549958 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.1510. Min Act: -0.1700
Data Index: 3837949 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.1823. Min Act: -0.1700
Data Index: 4969166 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.1198. Min Act: -0.1700
Data Index: 907077 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5261. Min Range: -4.5261
Max Act: 4.1198. Min Act: -0.1700
Data Index: 482307 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19