Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2165 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.4981. Min Act: -0.1700
Data Index: 5405596 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.2481. Min Act: -0.1700
Data Index: 2372078 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.2481. Min Act: -0.1700
Data Index: 3030999 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.2168. Min Act: -0.1700
Data Index: 5368664 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.1231. Min Act: -0.1700
Data Index: 8671314 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.0918. Min Act: -0.1700
Data Index: 1332124 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.0606. Min Act: -0.1700
Data Index: 872098 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.0606. Min Act: -0.1700
Data Index: 6660893 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.0606. Min Act: -0.1700
Data Index: 3975476 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.0293. Min Act: -0.1700
Data Index: 2510075 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.0293. Min Act: -0.1700
Data Index: 5674403 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4981. Min Range: -5.4981
Max Act: 5.0293. Min Act: -0.1700
Data Index: 6619387 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4981. Min Range: -5.4981
Max Act: 4.9981. Min Act: -0.1700
Data Index: 6977070 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4981. Min Range: -5.4981
Max Act: 4.9668. Min Act: -0.1700
Data Index: 4308596 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4981. Min Range: -5.4981
Max Act: 4.9981. Min Act: -0.1700
Data Index: 5278587 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4981. Min Range: -5.4981
Max Act: 4.9668. Min Act: -0.1700
Data Index: 208655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4981. Min Range: -5.4981
Max Act: 4.9668. Min Act: -0.1700
Data Index: 2096689 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4981. Min Range: -5.4981
Max Act: 4.9356. Min Act: -0.1700
Data Index: 6136657 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4981. Min Range: -5.4981
Max Act: 4.9356. Min Act: -0.1700
Data Index: 4979382 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4981. Min Range: -5.4981
Max Act: 4.9668. Min Act: -0.1700
Data Index: 5819183 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19