Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1149 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3877. Min Range: -4.3877
Max Act: 4.3877. Min Act: -0.1700
Data Index: 2965685 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3877. Min Range: -4.3877
Max Act: 4.2314. Min Act: -0.1700
Data Index: 8819750 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3877. Min Range: -4.3877
Max Act: 4.0751. Min Act: -0.1700
Data Index: 3403811 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3877. Min Range: -4.3877
Max Act: 4.0439. Min Act: -0.1700
Data Index: 6523497 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3877. Min Range: -4.3877
Max Act: 4.0126. Min Act: -0.1700
Data Index: 557576 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3877. Min Range: -4.3877
Max Act: 4.0126. Min Act: -0.1700
Data Index: 7323174 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9501. Min Act: -0.1700
Data Index: 7937707 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9813. Min Act: -0.1700
Data Index: 1965216 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9813. Min Act: -0.1700
Data Index: 4531681 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9813. Min Act: -0.1700
Data Index: 2120376 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9501. Min Act: -0.1700
Data Index: 7759189 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9188. Min Act: -0.1700
Data Index: 4270312 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9501. Min Act: -0.1700
Data Index: 2928689 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9188. Min Act: -0.1700
Data Index: 7726509 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9188. Min Act: -0.1700
Data Index: 7323173 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.8876. Min Act: -0.1700
Data Index: 4523661 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.9188. Min Act: -0.1700
Data Index: 7978857 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.8876. Min Act: -0.1700
Data Index: 4531680 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.8563. Min Act: -0.1700
Data Index: 7728913 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3877. Min Range: -4.3877
Max Act: 3.8876. Min Act: -0.1700
Data Index: 3180396 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19