Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 951 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2217. Min Range: -5.2217
Max Act: 5.2217. Min Act: -0.1700
Data Index: 7422740 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2217. Min Range: -5.2217
Max Act: 5.0967. Min Act: -0.1700
Data Index: 4972425 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2217. Min Range: -5.2217
Max Act: 5.0030. Min Act: -0.1700
Data Index: 5172467 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2217. Min Range: -5.2217
Max Act: 5.0030. Min Act: -0.1700
Data Index: 8688279 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2217. Min Range: -5.2217
Max Act: 5.0030. Min Act: -0.1700
Data Index: 8371822 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.9717. Min Act: -0.1700
Data Index: 1352309 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.9405. Min Act: -0.1700
Data Index: 7065192 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.9717. Min Act: -0.1700
Data Index: 8494413 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.9405. Min Act: -0.1700
Data Index: 3038091 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.8780. Min Act: -0.1700
Data Index: 6705677 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.9092. Min Act: -0.1700
Data Index: 5553613 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.9092. Min Act: -0.1700
Data Index: 1379648 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.8780. Min Act: -0.1700
Data Index: 1624167 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.8780. Min Act: -0.1700
Data Index: 4661117 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.9092. Min Act: -0.1700
Data Index: 7500066 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.9405. Min Act: -0.1700
Data Index: 7496007 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.8155. Min Act: -0.1700
Data Index: 6659931 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.8780. Min Act: -0.1700
Data Index: 2117458 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.8467. Min Act: -0.1700
Data Index: 6081385 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2217. Min Range: -5.2217
Max Act: 4.8155. Min Act: -0.1700
Data Index: 1865193 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19