Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 150 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.5201. Min Act: -0.1700
Data Index: 3799876 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4888. Min Act: -0.1700
Data Index: 4872699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4888. Min Act: -0.1700
Data Index: 342070 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4888. Min Act: -0.1700
Data Index: 7247298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4888. Min Act: -0.1700
Data Index: 1001812 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4574. Min Act: -0.1700
Data Index: 2270466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4261. Min Act: -0.1700
Data Index: 5120917 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4574. Min Act: -0.1700
Data Index: 175341 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4574. Min Act: -0.1700
Data Index: 8367348 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4574. Min Act: -0.1700
Data Index: 6949966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4574. Min Act: -0.1700
Data Index: 2532644 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4574. Min Act: -0.1700
Data Index: 6461387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4261. Min Act: -0.1700
Data Index: 6408385 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4261. Min Act: -0.1700
Data Index: 5120922 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4261. Min Act: -0.1700
Data Index: 556537 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4261. Min Act: -0.1700
Data Index: 2791329 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4261. Min Act: -0.1700
Data Index: 2856271 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4261. Min Act: -0.1700
Data Index: 1293441 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4261. Min Act: -0.1700
Data Index: 3004168 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5201. Min Range: -3.5201
Max Act: 3.4261. Min Act: -0.1700
Data Index: 3326344 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19