Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.7031. Min Act: -0.1700
Data Index: 1992669 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.5156. Min Act: -0.1700
Data Index: 1939659 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.4218. Min Act: -0.1700
Data Index: 8451178 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.3906. Min Act: -0.1700
Data Index: 4644383 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.3281. Min Act: -0.1700
Data Index: 6547104 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.3281. Min Act: -0.1700
Data Index: 3484530 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.3281. Min Act: -0.1700
Data Index: 3484523 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.3593. Min Act: -0.1700
Data Index: 2682151 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.3281. Min Act: -0.1700
Data Index: 6777340 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.2968. Min Act: -0.1700
Data Index: 2293297 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.2968. Min Act: -0.1700
Data Index: 6477814 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.2343. Min Act: -0.1700
Data Index: 4352562 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.2343. Min Act: -0.1700
Data Index: 5230779 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.2030. Min Act: -0.1700
Data Index: 6462532 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.2343. Min Act: -0.1700
Data Index: 1666225 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.2030. Min Act: -0.1700
Data Index: 1197318 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.2030. Min Act: -0.1700
Data Index: 6709754 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.1718. Min Act: -0.1700
Data Index: 3450318 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.1405. Min Act: -0.1700
Data Index: 3501578 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7031. Min Range: -4.7031
Max Act: 4.1405. Min Act: -0.1700
Data Index: 1215565 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19