Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1268. Min Range: -8.1268
Max Act: 8.1268. Min Act: -0.1696
Data Index: 7545130 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.6268. Min Act: -0.1700
Data Index: 7737070 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.6893. Min Act: -0.1700
Data Index: 3987277 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.6268. Min Act: -0.1700
Data Index: 6912786 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.4081. Min Act: -0.1700
Data Index: 4892291 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.1893. Min Act: -0.1700
Data Index: 5743148 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.1893. Min Act: -0.1700
Data Index: 5206294 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.2206. Min Act: -0.1700
Data Index: 2984017 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.1893. Min Act: -0.1700
Data Index: 6515197 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.2206. Min Act: -0.1697
Data Index: 3184619 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.2206. Min Act: -0.1700
Data Index: 1052096 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.1268. Min Act: -0.1699
Data Index: 2484526 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.2206. Min Act: -0.1698
Data Index: 4402169 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1268. Min Range: -8.1268
Max Act: 6.9706. Min Act: -0.1698
Data Index: 6980721 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 814091 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.1893. Min Act: -0.1700
Data Index: 1786991 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 6330462 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.0956. Min Act: -0.1697
Data Index: 2357151 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 6041138 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1268. Min Range: -8.1268
Max Act: 7.2518. Min Act: -0.1700
Data Index: 3435510 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19