Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.2163. Min Act: -0.1700
Data Index: 7272516 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1849. Min Act: -0.1700
Data Index: 5015944 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1849. Min Act: -0.1700
Data Index: 1619203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1849. Min Act: -0.1700
Data Index: 5099965 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1692. Min Act: -0.1700
Data Index: 1300827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1377. Min Act: -0.1700
Data Index: 4570012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1219. Min Act: -0.1700
Data Index: 8491830 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1377. Min Act: -0.1700
Data Index: 1648364 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1377. Min Act: -0.1700
Data Index: 7149626 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1219. Min Act: -0.1700
Data Index: 343846 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1219. Min Act: -0.1700
Data Index: 1487086 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.1062. Min Act: -0.1700
Data Index: 2736051 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.0904. Min Act: -0.1700
Data Index: 1802289 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.0904. Min Act: -0.1700
Data Index: 4650674 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.0904. Min Act: -0.1700
Data Index: 4998406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.0904. Min Act: -0.1700
Data Index: 1326825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.0904. Min Act: -0.1700
Data Index: 13785 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.0904. Min Act: -0.1700
Data Index: 6127599 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.0904. Min Act: -0.1700
Data Index: 7669293 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2163. Min Range: -3.2163
Max Act: 3.0904. Min Act: -0.1700
Data Index: 3488986 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19