Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 8829097 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 7726509 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 4963728 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 3261448 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 5655967 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 3769833 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 1520642 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 8303989 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 2555959 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 5813182 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 4425995 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2016. Min Act: -0.1700
Data Index: 3459374 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1858. Min Act: -0.1700
Data Index: 6147169 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1701. Min Act: -0.1700
Data Index: 2928689 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1701. Min Act: -0.1700
Data Index: 8756399 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1701. Min Act: -0.1700
Data Index: 6730759 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1386. Min Act: -0.1700
Data Index: 8023354 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1544. Min Act: -0.1700
Data Index: 8746573 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1386. Min Act: -0.1700
Data Index: 6924183 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1229. Min Act: -0.1700
Data Index: 3783420 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19