Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2664. Min Range: -3.2664
Max Act: 3.2664. Min Act: -0.1700
Data Index: 3339411 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2664. Min Range: -3.2664
Max Act: 3.1249. Min Act: -0.1700
Data Index: 2312153 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2664. Min Range: -3.2664
Max Act: 3.0145. Min Act: -0.1700
Data Index: 8712326 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2664. Min Range: -3.2664
Max Act: 3.0145. Min Act: -0.1700
Data Index: 416156 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9987. Min Act: -0.1700
Data Index: 5011154 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9670. Min Act: -0.1700
Data Index: 1953043 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9670. Min Act: -0.1700
Data Index: 6637726 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9512. Min Act: -0.1700
Data Index: 5204217 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9512. Min Act: -0.1700
Data Index: 5444962 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9195. Min Act: -0.1700
Data Index: 6410755 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9354. Min Act: -0.1700
Data Index: 8382871 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9037. Min Act: -0.1700
Data Index: 6353309 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9037. Min Act: -0.1700
Data Index: 7955674 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9195. Min Act: -0.1700
Data Index: 3787268 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.8878. Min Act: -0.1700
Data Index: 1391965 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9037. Min Act: -0.1700
Data Index: 8421373 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.8878. Min Act: -0.1700
Data Index: 1355352 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.8719. Min Act: -0.1700
Data Index: 276301 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.9037. Min Act: -0.1700
Data Index: 1355351 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2664. Min Range: -3.2664
Max Act: 2.8561. Min Act: -0.1700
Data Index: 5682669 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19