Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2168 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1691. Min Range: -4.1691
Max Act: 4.1691. Min Act: -0.1700
Data Index: 194499 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1691. Min Range: -4.1691
Max Act: 4.1066. Min Act: -0.1700
Data Index: 1136331 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1691. Min Range: -4.1691
Max Act: 4.0753. Min Act: -0.1700
Data Index: 3575512 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1691. Min Range: -4.1691
Max Act: 4.0128. Min Act: -0.1700
Data Index: 8769123 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.9815. Min Act: -0.1700
Data Index: 1136332 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.9190. Min Act: -0.1700
Data Index: 1301114 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.9034. Min Act: -0.1700
Data Index: 7871223 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.9034. Min Act: -0.1700
Data Index: 1973297 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.8252. Min Act: -0.1700
Data Index: 2131181 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.8252. Min Act: -0.1700
Data Index: 7242354 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7939. Min Act: -0.1700
Data Index: 4380018 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7783. Min Act: -0.1700
Data Index: 6526793 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7627. Min Act: -0.1700
Data Index: 3813757 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7783. Min Act: -0.1700
Data Index: 4403152 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7627. Min Act: -0.1700
Data Index: 5067089 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7627. Min Act: -0.1700
Data Index: 4563197 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7470. Min Act: -0.1700
Data Index: 5444907 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7314. Min Act: -0.1700
Data Index: 8526708 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7157. Min Act: -0.1700
Data Index: 3371022 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1691. Min Range: -4.1691
Max Act: 3.7001. Min Act: -0.1700
Data Index: 2004077 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19