Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4069 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.2793. Min Act: -0.1700
Data Index: 8208917 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.2164. Min Act: -0.1700
Data Index: 834694 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.2164. Min Act: -0.1700
Data Index: 3454195 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.2164. Min Act: -0.1700
Data Index: 4656639 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.1692. Min Act: -0.1700
Data Index: 3455547 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.1535. Min Act: -0.1700
Data Index: 3429126 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.1850. Min Act: -0.1700
Data Index: 1254394 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.1378. Min Act: -0.1700
Data Index: 2559742 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.1535. Min Act: -0.1700
Data Index: 6240186 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.1535. Min Act: -0.1700
Data Index: 4202239 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.1535. Min Act: -0.1700
Data Index: 3533951 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.0905. Min Act: -0.1700
Data Index: 1715927 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.1220. Min Act: -0.1700
Data Index: 6207742 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.1220. Min Act: -0.1700
Data Index: 2006674 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.0905. Min Act: -0.1700
Data Index: 3208276 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.0905. Min Act: -0.1700
Data Index: 1513805 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.0590. Min Act: -0.1700
Data Index: 5678861 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.0747. Min Act: -0.1700
Data Index: 4812860 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.0747. Min Act: -0.1700
Data Index: 5753253 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2793. Min Range: -3.2793
Max Act: 3.0747. Min Act: -0.1700
Data Index: 5590064 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19