Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1789 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.3083. Min Act: -0.1700
Data Index: 5646029 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2754. Min Act: -0.1700
Data Index: 8147924 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2919. Min Act: -0.1700
Data Index: 6663048 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2919. Min Act: -0.1700
Data Index: 5294206 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2589. Min Act: -0.1700
Data Index: 7451568 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2589. Min Act: -0.1700
Data Index: 31768 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2424. Min Act: -0.1700
Data Index: 6111817 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2424. Min Act: -0.1700
Data Index: 1247235 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2424. Min Act: -0.1700
Data Index: 1342473 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2424. Min Act: -0.1700
Data Index: 1798050 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2424. Min Act: -0.1700
Data Index: 8690621 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2424. Min Act: -0.1700
Data Index: 8443682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2424. Min Act: -0.1700
Data Index: 2052486 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2424. Min Act: -0.1700
Data Index: 1494338 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2259. Min Act: -0.1700
Data Index: 6110847 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2424. Min Act: -0.1700
Data Index: 7210573 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.2093. Min Act: -0.1700
Data Index: 1950910 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.1927. Min Act: -0.1700
Data Index: 8216084 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.1927. Min Act: -0.1700
Data Index: 6760330 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3083. Min Range: -2.3083
Max Act: 2.1927. Min Act: -0.1700
Data Index: 6957190 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19