Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.8173. Min Act: -0.1700
Data Index: 1901087 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.7235. Min Act: -0.1700
Data Index: 6948009 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.7235. Min Act: -0.1700
Data Index: 8726381 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6922. Min Act: -0.1700
Data Index: 6971208 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6922. Min Act: -0.1700
Data Index: 7393561 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6922. Min Act: -0.1700
Data Index: 1378233 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6922. Min Act: -0.1700
Data Index: 6838106 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6609. Min Act: -0.1700
Data Index: 3537558 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6296. Min Act: -0.1700
Data Index: 5662628 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6296. Min Act: -0.1700
Data Index: 1347983 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6609. Min Act: -0.1700
Data Index: 4705854 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6296. Min Act: -0.1700
Data Index: 4607083 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6609. Min Act: -0.1700
Data Index: 5081988 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.5983. Min Act: -0.1700
Data Index: 3986382 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.5983. Min Act: -0.1700
Data Index: 1637791 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6296. Min Act: -0.1700
Data Index: 873862 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6296. Min Act: -0.1700
Data Index: 3171568 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6296. Min Act: -0.1700
Data Index: 3371833 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6296. Min Act: -0.1700
Data Index: 8152079 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8173. Min Range: -3.8173
Max Act: 3.6296. Min Act: -0.1700
Data Index: 8255300 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19