Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 378 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.3335. Min Act: -0.1700
Data Index: 2183411 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.2085. Min Act: -0.1700
Data Index: 5550664 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.1460. Min Act: -0.1700
Data Index: 1127374 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.1460. Min Act: -0.1700
Data Index: 2814725 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.1460. Min Act: -0.1700
Data Index: 4449015 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0834. Min Act: -0.1700
Data Index: 8132239 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0522. Min Act: -0.1700
Data Index: 6226911 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0834. Min Act: -0.1700
Data Index: 6941501 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0522. Min Act: -0.1700
Data Index: 401555 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0834. Min Act: -0.1700
Data Index: 1345186 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0209. Min Act: -0.1700
Data Index: 4193652 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0522. Min Act: -0.1700
Data Index: 8074303 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0209. Min Act: -0.1700
Data Index: 8291453 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0209. Min Act: -0.1700
Data Index: 2010386 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0209. Min Act: -0.1700
Data Index: 1770959 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3335. Min Range: -4.3335
Max Act: 3.9897. Min Act: -0.1700
Data Index: 5412327 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3335. Min Range: -4.3335
Max Act: 3.9584. Min Act: -0.1700
Data Index: 7029287 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0209. Min Act: -0.1700
Data Index: 7051981 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3335. Min Range: -4.3335
Max Act: 4.0209. Min Act: -0.1700
Data Index: 3473803 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3335. Min Range: -4.3335
Max Act: 3.9584. Min Act: -0.1700
Data Index: 7053652 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19