Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2578 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.6462. Min Act: -0.1700
Data Index: 5776452 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.5212. Min Act: -0.1700
Data Index: 8007434 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.1462. Min Act: -0.1700
Data Index: 8459500 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.0525. Min Act: -0.1700
Data Index: 5410554 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6462. Min Range: -6.6462
Max Act: 6.0212. Min Act: -0.1700
Data Index: 1601064 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.9900. Min Act: -0.1700
Data Index: 3989643 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.8650. Min Act: -0.1700
Data Index: 1653265 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.8337. Min Act: -0.1700
Data Index: 2353377 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.8025. Min Act: -0.1700
Data Index: 3808376 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.7712. Min Act: -0.1700
Data Index: 8632563 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.7400. Min Act: -0.1700
Data Index: 6666937 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.8025. Min Act: -0.1700
Data Index: 2941832 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.7400. Min Act: -0.1700
Data Index: 415051 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.7087. Min Act: -0.1700
Data Index: 4353583 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.6775. Min Act: -0.1700
Data Index: 4395337 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.7400. Min Act: -0.1700
Data Index: 3559746 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.7087. Min Act: -0.1700
Data Index: 6828507 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.7087. Min Act: -0.1700
Data Index: 7088222 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.7087. Min Act: -0.1700
Data Index: 7353115 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6462. Min Range: -6.6462
Max Act: 5.6775. Min Act: -0.1700
Data Index: 2134333 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19