Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3418. Min Range: -3.3418
Max Act: 3.3418. Min Act: -0.1700
Data Index: 5367216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3418. Min Range: -3.3418
Max Act: 3.0587. Min Act: -0.1700
Data Index: 5892855 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3418. Min Range: -3.3418
Max Act: 3.0271. Min Act: -0.1700
Data Index: 3587535 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.9797. Min Act: -0.1700
Data Index: 5057781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3418. Min Range: -3.3418
Max Act: 3.0113. Min Act: -0.1700
Data Index: 2314266 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8846. Min Act: -0.1700
Data Index: 390818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.9164. Min Act: -0.1700
Data Index: 2444530 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.9164. Min Act: -0.1700
Data Index: 359356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8370. Min Act: -0.1700
Data Index: 6694694 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8688. Min Act: -0.1700
Data Index: 8363618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8688. Min Act: -0.1700
Data Index: 640031 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8370. Min Act: -0.1700
Data Index: 2529202 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8211. Min Act: -0.1700
Data Index: 2810289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8529. Min Act: -0.1700
Data Index: 3447563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8370. Min Act: -0.1700
Data Index: 2561153 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8370. Min Act: -0.1700
Data Index: 7017142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.8052. Min Act: -0.1700
Data Index: 1006072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.7733. Min Act: -0.1700
Data Index: 1328712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.7574. Min Act: -0.1700
Data Index: 2114104 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3418. Min Range: -3.3418
Max Act: 2.7414. Min Act: -0.1700
Data Index: 2996938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19