Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 305 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.3735. Min Act: -0.1700
Data Index: 3592760 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.3735. Min Act: -0.1700
Data Index: 6770931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.3421. Min Act: -0.1700
Data Index: 8831901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.3421. Min Act: -0.1700
Data Index: 7564642 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.3421. Min Act: -0.1700
Data Index: 5586037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.3107. Min Act: -0.1700
Data Index: 8425787 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.3107. Min Act: -0.1700
Data Index: 4263538 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.3107. Min Act: -0.1700
Data Index: 5576130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 7308507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 7129076 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 6851164 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 656154 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 5859752 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2479. Min Act: -0.1700
Data Index: 4440834 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 4343670 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 1495187 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 4260253 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 3847282 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 1234475 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3735. Min Range: -3.3735
Max Act: 3.2793. Min Act: -0.1700
Data Index: 1119260 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19