Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.9377. Min Act: -0.1700
Data Index: 7802594 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.9292. Min Act: -0.1700
Data Index: 705658 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8780. Min Act: -0.1700
Data Index: 2524990 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8951. Min Act: -0.1700
Data Index: 7237273 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8695. Min Act: -0.1700
Data Index: 7124192 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8866. Min Act: -0.1700
Data Index: 8123005 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8695. Min Act: -0.1700
Data Index: 7048888 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8695. Min Act: -0.1674
Data Index: 4743668 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8438. Min Act: -0.1697
Data Index: 5961679 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8438. Min Act: -0.1700
Data Index: 4468839 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8267. Min Act: -0.1700
Data Index: 1466139 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8267. Min Act: -0.1700
Data Index: 1080593 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8438. Min Act: -0.1700
Data Index: 1987077 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8267. Min Act: -0.1700
Data Index: 5848754 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8438. Min Act: -0.1698
Data Index: 3209667 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8181. Min Act: -0.1700
Data Index: 1096423 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8095. Min Act: -0.1700
Data Index: 4468829 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8352. Min Act: -0.1700
Data Index: 3016504 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.7923. Min Act: -0.1700
Data Index: 6498916 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9377. Min Range: -1.9377
Max Act: 1.8009. Min Act: -0.1700
Data Index: 7237275 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19