Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3866 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0365. Min Range: -5.0365
Max Act: 5.0365. Min Act: -0.1700
Data Index: 7591057 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.9740. Min Act: -0.1700
Data Index: 2540272 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.9427. Min Act: -0.1700
Data Index: 4840487 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.9427. Min Act: -0.1700
Data Index: 8616314 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8802. Min Act: -0.1700
Data Index: 2287210 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8802. Min Act: -0.1700
Data Index: 4557228 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8802. Min Act: -0.1700
Data Index: 7386628 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8802. Min Act: -0.1700
Data Index: 7189519 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8802. Min Act: -0.1700
Data Index: 5638464 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8802. Min Act: -0.1700
Data Index: 2197701 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8490. Min Act: -0.1700
Data Index: 1237324 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8177. Min Act: -0.1700
Data Index: 227047 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8490. Min Act: -0.1700
Data Index: 7480791 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8490. Min Act: -0.1700
Data Index: 6856961 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8490. Min Act: -0.1700
Data Index: 7932545 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8490. Min Act: -0.1700
Data Index: 3438657 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8177. Min Act: -0.1700
Data Index: 7649303 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8177. Min Act: -0.1700
Data Index: 8251437 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8177. Min Act: -0.1700
Data Index: 3696490 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8802. Min Act: -0.1700
Data Index: 1237320 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19