Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.6565. Min Act: -0.1700
Data Index: 8638092 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.5000. Min Act: -0.1700
Data Index: 100155 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3746. Min Act: -0.1700
Data Index: 7537707 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3903. Min Act: -0.1700
Data Index: 7927751 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3903. Min Act: -0.1700
Data Index: 7747861 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3432. Min Act: -0.1700
Data Index: 4291726 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3432. Min Act: -0.1700
Data Index: 2576846 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3589. Min Act: -0.1700
Data Index: 100156 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3119. Min Act: -0.1700
Data Index: 2130769 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3276. Min Act: -0.1700
Data Index: 8232376 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2962. Min Act: -0.1700
Data Index: 8349471 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2962. Min Act: -0.1700
Data Index: 8638090 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2962. Min Act: -0.1700
Data Index: 6890152 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2805. Min Act: -0.1700
Data Index: 1180059 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2962. Min Act: -0.1700
Data Index: 6605225 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2962. Min Act: -0.1700
Data Index: 5529803 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2490. Min Act: -0.1700
Data Index: 3431560 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2805. Min Act: -0.1700
Data Index: 2503851 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2648. Min Act: -0.1700
Data Index: 469167 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.2648. Min Act: -0.1700
Data Index: 8638089 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19