Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4081 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.9735. Min Act: -0.1700
Data Index: 1423374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.9423. Min Act: -0.1700
Data Index: 343141 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.9110. Min Act: -0.1700
Data Index: 8686349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.9110. Min Act: -0.1700
Data Index: 5160419 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8797. Min Act: -0.1700
Data Index: 1149137 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8485. Min Act: -0.1700
Data Index: 7729550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8485. Min Act: -0.1700
Data Index: 4500540 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8797. Min Act: -0.1700
Data Index: 5312056 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8485. Min Act: -0.1700
Data Index: 2755224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8485. Min Act: -0.1700
Data Index: 6306636 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8172. Min Act: -0.1700
Data Index: 6546165 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8172. Min Act: -0.1700
Data Index: 7251209 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8172. Min Act: -0.1700
Data Index: 7588149 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8172. Min Act: -0.1700
Data Index: 4352934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8172. Min Act: -0.1700
Data Index: 2139952 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8172. Min Act: -0.1700
Data Index: 8161378 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8172. Min Act: -0.1700
Data Index: 3210071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8172. Min Act: -0.1700
Data Index: 8193191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8485. Min Act: -0.1700
Data Index: 1290066 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9735. Min Range: -3.9735
Max Act: 3.8172. Min Act: -0.1700
Data Index: 5360153 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19