Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3934 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1137. Min Range: -1.1137
Max Act: 1.1137. Min Act: -0.1700
Data Index: 4608393 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1137. Min Range: -1.1137
Max Act: 1.0612. Min Act: -0.1700
Data Index: 1889919 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1137. Min Range: -1.1137
Max Act: 1.0438. Min Act: -0.1700
Data Index: 1322533 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1137. Min Range: -1.1137
Max Act: 1.0264. Min Act: -0.1700
Data Index: 8249905 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1137. Min Range: -1.1137
Max Act: 1.0177. Min Act: -0.1700
Data Index: 1735930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1137. Min Range: -1.1137
Max Act: 1.0177. Min Act: -0.1700
Data Index: 2949162 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1137. Min Range: -1.1137
Max Act: 1.0090. Min Act: -0.1700
Data Index: 6966700 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1137. Min Range: -1.1137
Max Act: 1.0003. Min Act: -0.1700
Data Index: 3543730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9916. Min Act: -0.1700
Data Index: 6753952 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9916. Min Act: -0.1700
Data Index: 8494094 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9916. Min Act: -0.1700
Data Index: 4307289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9743. Min Act: -0.1700
Data Index: 22238 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9830. Min Act: -0.1700
Data Index: 3724390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9916. Min Act: -0.1700
Data Index: 7410335 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9830. Min Act: -0.1700
Data Index: 5233279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9743. Min Act: -0.1700
Data Index: 6538424 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9830. Min Act: -0.1700
Data Index: 3345343 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9743. Min Act: -0.1700
Data Index: 3477307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9657. Min Act: -0.1700
Data Index: 3747719 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1137. Min Range: -1.1137
Max Act: 0.9743. Min Act: -0.1700
Data Index: 2422845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19