Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 588 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2180. Min Range: -4.2180
Max Act: 4.2180. Min Act: -0.1700
Data Index: 8232259 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2180. Min Range: -4.2180
Max Act: 4.1243. Min Act: -0.1700
Data Index: 4412818 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2180. Min Range: -4.2180
Max Act: 4.1243. Min Act: -0.1700
Data Index: 7665012 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2180. Min Range: -4.2180
Max Act: 4.0930. Min Act: -0.1700
Data Index: 3648741 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2180. Min Range: -4.2180
Max Act: 4.0617. Min Act: -0.1700
Data Index: 8216274 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2180. Min Range: -4.2180
Max Act: 4.0617. Min Act: -0.1700
Data Index: 5837390 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2180. Min Range: -4.2180
Max Act: 4.0617. Min Act: -0.1700
Data Index: 3135023 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2180. Min Range: -4.2180
Max Act: 4.0305. Min Act: -0.1700
Data Index: 4615934 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2180. Min Range: -4.2180
Max Act: 4.0617. Min Act: -0.1700
Data Index: 2757866 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9992. Min Act: -0.1700
Data Index: 3112185 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9680. Min Act: -0.1700
Data Index: 7214722 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9992. Min Act: -0.1700
Data Index: 609869 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9992. Min Act: -0.1700
Data Index: 5090329 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9992. Min Act: -0.1700
Data Index: 3764433 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9992. Min Act: -0.1700
Data Index: 2613318 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9992. Min Act: -0.1700
Data Index: 7583031 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9054. Min Act: -0.1700
Data Index: 5681117 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9680. Min Act: -0.1700
Data Index: 5739342 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9680. Min Act: -0.1700
Data Index: 3944729 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2180. Min Range: -4.2180
Max Act: 3.9992. Min Act: -0.1700
Data Index: 6046003 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19