Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.2589. Min Act: -0.1700
Data Index: 1015595 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.2276. Min Act: -0.1700
Data Index: 8076746 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.2276. Min Act: -0.1700
Data Index: 3537346 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.1651. Min Act: -0.1700
Data Index: 7267032 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.1339. Min Act: -0.1700
Data Index: 6842538 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.1339. Min Act: -0.1700
Data Index: 394980 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0401. Min Act: -0.1700
Data Index: 4261290 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0401. Min Act: -0.1700
Data Index: 5974650 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0714. Min Act: -0.1700
Data Index: 4146253 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0401. Min Act: -0.1700
Data Index: 1138203 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0401. Min Act: -0.1700
Data Index: 1898814 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0089. Min Act: -0.1700
Data Index: 1797208 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0401. Min Act: -0.1700
Data Index: 2457656 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0401. Min Act: -0.1700
Data Index: 4929032 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2589. Min Range: -5.2589
Max Act: 4.9776. Min Act: -0.1700
Data Index: 4798950 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0089. Min Act: -0.1700
Data Index: 55244 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2589. Min Range: -5.2589
Max Act: 4.9464. Min Act: -0.1700
Data Index: 6624497 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2589. Min Range: -5.2589
Max Act: 4.9776. Min Act: -0.1700
Data Index: 4929030 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2589. Min Range: -5.2589
Max Act: 4.9464. Min Act: -0.1700
Data Index: 4149547 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2589. Min Range: -5.2589
Max Act: 5.0089. Min Act: -0.1700
Data Index: 6001572 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19