Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3434 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3540. Min Range: -5.3540
Max Act: 5.3540. Min Act: -0.1700
Data Index: 7656121 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3540. Min Range: -5.3540
Max Act: 5.3227. Min Act: -0.1700
Data Index: 8316601 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3540. Min Range: -5.3540
Max Act: 5.1665. Min Act: -0.1700
Data Index: 5708968 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3540. Min Range: -5.3540
Max Act: 5.0727. Min Act: -0.1700
Data Index: 6912638 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3540. Min Range: -5.3540
Max Act: 5.0415. Min Act: -0.1700
Data Index: 7694578 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3540. Min Range: -5.3540
Max Act: 5.0102. Min Act: -0.1700
Data Index: 1980584 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9790. Min Act: -0.1700
Data Index: 3650685 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3540. Min Range: -5.3540
Max Act: 5.0415. Min Act: -0.1700
Data Index: 8761021 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9790. Min Act: -0.1700
Data Index: 3454180 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9477. Min Act: -0.1700
Data Index: 1674200 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9790. Min Act: -0.1700
Data Index: 6715089 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9790. Min Act: -0.1700
Data Index: 6328447 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9477. Min Act: -0.1700
Data Index: 4757507 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9165. Min Act: -0.1700
Data Index: 8249558 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9477. Min Act: -0.1700
Data Index: 7870901 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.8852. Min Act: -0.1700
Data Index: 8262453 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9165. Min Act: -0.1700
Data Index: 3782930 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9477. Min Act: -0.1700
Data Index: 4285513 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9165. Min Act: -0.1700
Data Index: 7065295 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3540. Min Range: -5.3540
Max Act: 4.9165. Min Act: -0.1700
Data Index: 4397345 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19