Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.9849. Min Act: -0.1700
Data Index: 5661938 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.9849. Min Act: -0.1700
Data Index: 567871 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.8599. Min Act: -0.1700
Data Index: 8759214 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.8599. Min Act: -0.1700
Data Index: 804307 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.6724. Min Act: -0.1700
Data Index: 1444847 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.6724. Min Act: -0.1700
Data Index: 7398720 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.5474. Min Act: -0.1700
Data Index: 2909240 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.4849. Min Act: -0.1700
Data Index: 8038155 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.5474. Min Act: -0.1700
Data Index: 2909238 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.3599. Min Act: -0.1700
Data Index: 704621 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.3599. Min Act: -0.1700
Data Index: 4723745 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.4224. Min Act: -0.1700
Data Index: 1545161 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.1724. Min Act: -0.1700
Data Index: 2887347 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.1724. Min Act: -0.1700
Data Index: 2887346 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.2974. Min Act: -0.1700
Data Index: 8254320 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.2349. Min Act: -0.1700
Data Index: 170580 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.2349. Min Act: -0.1700
Data Index: 2909236 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.1099. Min Act: -0.1700
Data Index: 6259980 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.1724. Min Act: -0.1700
Data Index: 111210 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9849. Min Range: -8.9849
Max Act: 8.1099. Min Act: -0.1700
Data Index: 2909235 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19