Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8922. Min Range: -5.8922
Max Act: 5.8922. Min Act: -0.1700
Data Index: 8301128 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8922. Min Range: -5.8922
Max Act: 5.3609. Min Act: -0.1700
Data Index: 8301126 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8922. Min Range: -5.8922
Max Act: 5.1734. Min Act: -0.1700
Data Index: 257231 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8922. Min Range: -5.8922
Max Act: 5.0484. Min Act: -0.1700
Data Index: 6327009 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.7047. Min Act: -0.1700
Data Index: 7142352 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.7047. Min Act: -0.1700
Data Index: 6070015 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.5172. Min Act: -0.1700
Data Index: 196892 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.5172. Min Act: -0.1700
Data Index: 5155579 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.3921. Min Act: -0.1700
Data Index: 6780612 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.4234. Min Act: -0.1700
Data Index: 4338710 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.4546. Min Act: -0.1700
Data Index: 7191519 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.4234. Min Act: -0.1700
Data Index: 8718545 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.3921. Min Act: -0.1700
Data Index: 8150713 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.4234. Min Act: -0.1700
Data Index: 7191529 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.4234. Min Act: -0.1700
Data Index: 8070622 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.3921. Min Act: -0.1700
Data Index: 571877 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.3609. Min Act: -0.1700
Data Index: 1141630 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.3609. Min Act: -0.1700
Data Index: 7783057 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.3609. Min Act: -0.1700
Data Index: 1914793 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8922. Min Range: -5.8922
Max Act: 4.3609. Min Act: -0.1700
Data Index: 3134807 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19