Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1538 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.4161. Min Act: -0.1700
Data Index: 298970 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.3998. Min Act: -0.1700
Data Index: 4605597 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.3834. Min Act: -0.1698
Data Index: 1546811 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.3343. Min Act: -0.1700
Data Index: 6020936 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.3015. Min Act: -0.1700
Data Index: 699691 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.3015. Min Act: -0.1699
Data Index: 4029672 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.3015. Min Act: -0.1699
Data Index: 5922858 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.3015. Min Act: -0.1700
Data Index: 2625288 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2850. Min Act: -0.1700
Data Index: 298971 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.3015. Min Act: -0.1699
Data Index: 2625277 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2850. Min Act: -0.1700
Data Index: 5922854 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2850. Min Act: -0.1700
Data Index: 5838495 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2685. Min Act: -0.1700
Data Index: 511628 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2850. Min Act: -0.1700
Data Index: 8268578 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2850. Min Act: -0.1700
Data Index: 5142505 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2520. Min Act: -0.1700
Data Index: 5676643 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2355. Min Act: -0.1700
Data Index: 8000662 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2355. Min Act: -0.1700
Data Index: 4825120 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2520. Min Act: -0.1700
Data Index: 2625257 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4161. Min Range: -2.4161
Max Act: 2.2520. Min Act: -0.1700
Data Index: 2625287 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19