Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.6634. Min Act: -0.1632
Data Index: 1986156 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.5696. Min Act: -0.1698
Data Index: 1741744 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.4446. Min Act: -0.1697
Data Index: 8684519 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.4134. Min Act: -0.1691
Data Index: 7341259 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.4134. Min Act: -0.1697
Data Index: 4744350 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.3821. Min Act: -0.1630
Data Index: 4554732 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.3509. Min Act: -0.1700
Data Index: 6747128 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.3509. Min Act: -0.1690
Data Index: 4744348 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.3509. Min Act: -0.1700
Data Index: 1985390 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.3509. Min Act: -0.1700
Data Index: 5974170 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.3196. Min Act: -0.1700
Data Index: 4405238 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.3196. Min Act: -0.1697
Data Index: 4020094 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.3196. Min Act: -0.1700
Data Index: 1256642 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.2884. Min Act: -0.1700
Data Index: 8379559 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.2884. Min Act: -0.1700
Data Index: 5381198 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.2571. Min Act: -0.1659
Data Index: 7527146 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.2571. Min Act: -0.1700
Data Index: 6395325 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.2884. Min Act: -0.1700
Data Index: 2941866 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.2259. Min Act: -0.1700
Data Index: 4518048 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6634. Min Range: -5.6634
Max Act: 5.2259. Min Act: -0.1698
Data Index: 4744349 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19