Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1771. Min Range: -7.1771
Max Act: 7.1771. Min Act: -0.1652
Data Index: 8367994 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1771. Min Range: -7.1771
Max Act: 7.0209. Min Act: -0.1700
Data Index: 4795822 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.7709. Min Act: -0.1186
Data Index: 8368001 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.7396. Min Act: -0.1700
Data Index: 6318655 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.7084. Min Act: -0.1430
Data Index: 8367990 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.7084. Min Act: -0.1580
Data Index: 4274918 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.6771. Min Act: -0.1700
Data Index: 4379157 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.6459. Min Act: -0.1700
Data Index: 758251 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.7084. Min Act: -0.1698
Data Index: 6318654 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.6459. Min Act: -0.1617
Data Index: 8367988 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.6146. Min Act: -0.1700
Data Index: 4155776 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.6771. Min Act: -0.1700
Data Index: 6314291 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.6459. Min Act: -0.1700
Data Index: 7097822 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.6146. Min Act: -0.1215
Data Index: 4274923 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.5834. Min Act: -0.1700
Data Index: 8368005 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.5521. Min Act: -0.1694
Data Index: 237545 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.5521. Min Act: -0.1700
Data Index: 4446231 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.5834. Min Act: -0.1643
Data Index: 8367984 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.6146. Min Act: -0.1700
Data Index: 7320352 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1771. Min Range: -7.1771
Max Act: 6.5521. Min Act: -0.1700
Data Index: 4155772 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19