Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1825 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1409. Min Range: -4.1409
Max Act: 4.1409. Min Act: -0.1700
Data Index: 317563 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1409. Min Range: -4.1409
Max Act: 4.1096. Min Act: -0.1700
Data Index: 7524247 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1409. Min Range: -4.1409
Max Act: 4.1096. Min Act: -0.1700
Data Index: 5372260 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1409. Min Range: -4.1409
Max Act: 4.0784. Min Act: -0.1700
Data Index: 1170406 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.9846. Min Act: -0.1700
Data Index: 4185352 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.7501. Min Act: -0.1700
Data Index: 3276879 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6875. Min Act: -0.1700
Data Index: 5987755 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6875. Min Act: -0.1700
Data Index: 6215922 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.7031. Min Act: -0.1700
Data Index: 2772740 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.7031. Min Act: -0.1700
Data Index: 7067096 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.7031. Min Act: -0.1700
Data Index: 277803 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6719. Min Act: -0.1700
Data Index: 812264 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6875. Min Act: -0.1700
Data Index: 4698305 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6719. Min Act: -0.1700
Data Index: 3875254 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6719. Min Act: -0.1700
Data Index: 8636829 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6406. Min Act: -0.1700
Data Index: 5863002 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6719. Min Act: -0.1700
Data Index: 1943832 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6562. Min Act: -0.1700
Data Index: 5112745 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6406. Min Act: -0.1700
Data Index: 6623673 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1409. Min Range: -4.1409
Max Act: 3.6406. Min Act: -0.1700
Data Index: 4373727 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19