Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3747 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.4540. Min Act: -0.1700
Data Index: 17613 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.4696. Min Act: -0.1700
Data Index: 2585036 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.4696. Min Act: -0.1700
Data Index: 6563758 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.4226. Min Act: -0.1700
Data Index: 4413792 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.4069. Min Act: -0.1700
Data Index: 777789 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3599. Min Act: -0.1700
Data Index: 2712970 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3285. Min Act: -0.1700
Data Index: 2194533 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3442. Min Act: -0.1700
Data Index: 2675299 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3285. Min Act: -0.1700
Data Index: 6637726 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3442. Min Act: -0.1700
Data Index: 8406172 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3442. Min Act: -0.1700
Data Index: 5865302 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3285. Min Act: -0.1700
Data Index: 3246198 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3285. Min Act: -0.1700
Data Index: 6082179 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3128. Min Act: -0.1700
Data Index: 3362961 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.2971. Min Act: -0.1700
Data Index: 1737376 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3128. Min Act: -0.1700
Data Index: 6018047 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.2971. Min Act: -0.1700
Data Index: 2101352 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.3128. Min Act: -0.1700
Data Index: 5422668 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.2971. Min Act: -0.1700
Data Index: 5476704 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4696. Min Range: -3.4696
Max Act: 3.2971. Min Act: -0.1700
Data Index: 7953930 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19