Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.6267. Min Act: -0.1700
Data Index: 891423 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.5955. Min Act: -0.1700
Data Index: 4674956 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.4705. Min Act: -0.1700
Data Index: 2587857 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.3767. Min Act: -0.1700
Data Index: 6340514 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.3455. Min Act: -0.1700
Data Index: 4671235 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.2830. Min Act: -0.1700
Data Index: 8790400 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.2830. Min Act: -0.1700
Data Index: 7072814 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.2517. Min Act: -0.1700
Data Index: 4060970 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.2205. Min Act: -0.1700
Data Index: 504384 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.2205. Min Act: -0.1700
Data Index: 5654430 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.2205. Min Act: -0.1700
Data Index: 4651374 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.2205. Min Act: -0.1700
Data Index: 5654429 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.2517. Min Act: -0.1700
Data Index: 5788654 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.1580. Min Act: -0.1700
Data Index: 2707510 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.1892. Min Act: -0.1700
Data Index: 3107081 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.1267. Min Act: -0.1700
Data Index: 1883860 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.0955. Min Act: -0.1700
Data Index: 5413075 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.0330. Min Act: -0.1700
Data Index: 7839858 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.0017. Min Act: -0.1700
Data Index: 2943946 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6267. Min Range: -5.6267
Max Act: 5.0017. Min Act: -0.1700
Data Index: 4467571 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19