Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.1130. Min Act: -0.1700
Data Index: 487069 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0658. Min Act: -0.1700
Data Index: 685172 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0658. Min Act: -0.1700
Data Index: 5917912 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0658. Min Act: -0.1700
Data Index: 5214815 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0658. Min Act: -0.1700
Data Index: 6655656 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 4399271 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0658. Min Act: -0.1700
Data Index: 8210978 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 2400635 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 5411002 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 5743007 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 5074238 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 2561573 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0342. Min Act: -0.1700
Data Index: 5789704 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 1434552 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 3717779 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 5231040 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 6039499 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0500. Min Act: -0.1700
Data Index: 6125637 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0342. Min Act: -0.1700
Data Index: 5893925 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1130. Min Range: -3.1130
Max Act: 3.0342. Min Act: -0.1700
Data Index: 3585725 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19