Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0686. Min Range: -7.0686
Max Act: 7.0686. Min Act: -0.1700
Data Index: 6805663 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.9436. Min Act: -0.1700
Data Index: 6377848 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.9749. Min Act: -0.1700
Data Index: 216138 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.9749. Min Act: -0.1700
Data Index: 655286 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.9124. Min Act: -0.1700
Data Index: 424387 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.8186. Min Act: -0.1700
Data Index: 8505741 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.8811. Min Act: -0.1700
Data Index: 5151547 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.8499. Min Act: -0.1700
Data Index: 8453397 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.7874. Min Act: -0.1700
Data Index: 8796447 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.7874. Min Act: -0.1700
Data Index: 1741786 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.7561. Min Act: -0.1700
Data Index: 7199048 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.7249. Min Act: -0.1700
Data Index: 2104202 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.6624. Min Act: -0.1700
Data Index: 3473844 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.7249. Min Act: -0.1700
Data Index: 7239195 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.7249. Min Act: -0.1700
Data Index: 6456428 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.6936. Min Act: -0.1700
Data Index: 4314265 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.6311. Min Act: -0.1700
Data Index: 1076143 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.6311. Min Act: -0.1700
Data Index: 7239194 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.6311. Min Act: -0.1700
Data Index: 5994096 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0686. Min Range: -7.0686
Max Act: 6.5999. Min Act: -0.1700
Data Index: 152390 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19