Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4656 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8922. Min Act: -0.1700
Data Index: 6888376 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8609. Min Act: -0.1700
Data Index: 4009078 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8609. Min Act: -0.1700
Data Index: 786542 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8297. Min Act: -0.1700
Data Index: 4817379 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8297. Min Act: -0.1700
Data Index: 1911861 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8297. Min Act: -0.1700
Data Index: 3664215 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8297. Min Act: -0.1700
Data Index: 1911856 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7984. Min Act: -0.1700
Data Index: 1541502 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8297. Min Act: -0.1700
Data Index: 3664203 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 5337760 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.8297. Min Act: -0.1700
Data Index: 1911855 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7984. Min Act: -0.1700
Data Index: 1978412 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7984. Min Act: -0.1700
Data Index: 1911857 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 7716969 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7984. Min Act: -0.1700
Data Index: 7580265 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7984. Min Act: -0.1700
Data Index: 1145050 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7984. Min Act: -0.1700
Data Index: 1911854 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 3664213 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7984. Min Act: -0.1700
Data Index: 3806865 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8922. Min Range: -4.8922
Max Act: 4.7672. Min Act: -0.1700
Data Index: 1072763 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19