Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 530 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2802. Min Act: -0.1700
Data Index: 6512214 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2644. Min Act: -0.1700
Data Index: 8269365 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2487. Min Act: -0.1700
Data Index: 1337088 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2330. Min Act: -0.1700
Data Index: 3832824 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2330. Min Act: -0.1700
Data Index: 7100872 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2330. Min Act: -0.1700
Data Index: 421000 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2173. Min Act: -0.1700
Data Index: 1258308 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2330. Min Act: -0.1700
Data Index: 5134282 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2330. Min Act: -0.1700
Data Index: 8431571 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2330. Min Act: -0.1700
Data Index: 4061803 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2173. Min Act: -0.1700
Data Index: 7968572 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2173. Min Act: -0.1700
Data Index: 5477162 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2016. Min Act: -0.1700
Data Index: 1316331 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2173. Min Act: -0.1700
Data Index: 345904 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2173. Min Act: -0.1700
Data Index: 5675277 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2173. Min Act: -0.1700
Data Index: 2207724 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2016. Min Act: -0.1700
Data Index: 6813740 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2173. Min Act: -0.1700
Data Index: 2577760 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2173. Min Act: -0.1700
Data Index: 6851390 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2802. Min Range: -3.2802
Max Act: 3.2016. Min Act: -0.1700
Data Index: 7132366 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19