Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5592 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.8574. Min Act: -0.1699
Data Index: 2317901 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.8403. Min Act: -0.1690
Data Index: 259509 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.8232. Min Act: -0.1700
Data Index: 6340482 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.8060. Min Act: -0.1700
Data Index: 4118500 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7715. Min Act: -0.1700
Data Index: 1857154 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7715. Min Act: -0.1700
Data Index: 8138028 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7543. Min Act: -0.1700
Data Index: 8718046 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7370. Min Act: -0.1700
Data Index: 3992652 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7024. Min Act: -0.1699
Data Index: 3250831 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7197. Min Act: -0.1700
Data Index: 7457515 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7024. Min Act: -0.1700
Data Index: 3374156 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.6850. Min Act: -0.1700
Data Index: 6405388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7024. Min Act: -0.1700
Data Index: 4682520 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7024. Min Act: -0.1700
Data Index: 3375260 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7024. Min Act: -0.1700
Data Index: 6554946 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.6850. Min Act: -0.1700
Data Index: 6307801 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7024. Min Act: -0.1700
Data Index: 7732842 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.7024. Min Act: -0.1700
Data Index: 3952197 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.6850. Min Act: -0.1699
Data Index: 307233 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8574. Min Range: -1.8574
Max Act: 1.6850. Min Act: -0.1700
Data Index: 2215800 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19