Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4241 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.6424. Min Act: -0.1700
Data Index: 219114 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.4862. Min Act: -0.1700
Data Index: 747303 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.4549. Min Act: -0.1700
Data Index: 6051647 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.3612. Min Act: -0.1700
Data Index: 1056830 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.2674. Min Act: -0.1700
Data Index: 8310536 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.2362. Min Act: -0.1700
Data Index: 8749059 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.2049. Min Act: -0.1700
Data Index: 6475557 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.2049. Min Act: -0.1700
Data Index: 2313187 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.2049. Min Act: -0.1700
Data Index: 6447934 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.2049. Min Act: -0.1700
Data Index: 2890764 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.2049. Min Act: -0.1700
Data Index: 7967069 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.1737. Min Act: -0.1700
Data Index: 1593414 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.1737. Min Act: -0.1700
Data Index: 6219983 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.1424. Min Act: -0.1700
Data Index: 8602147 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.1424. Min Act: -0.1700
Data Index: 6305106 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.0799. Min Act: -0.1700
Data Index: 3691164 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.0487. Min Act: -0.1700
Data Index: 1246955 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.0174. Min Act: -0.1700
Data Index: 5484031 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.9862. Min Act: -0.1700
Data Index: 2792316 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.9862. Min Act: -0.1700
Data Index: 534717 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19