Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 844 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8915. Min Act: -0.1700
Data Index: 4920709 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8915. Min Act: -0.1700
Data Index: 6504592 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8915. Min Act: -0.1700
Data Index: 8305238 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8915. Min Act: -0.1700
Data Index: 7491775 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8603. Min Act: -0.1700
Data Index: 339182 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8603. Min Act: -0.1700
Data Index: 1668612 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8290. Min Act: -0.1700
Data Index: 4885331 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8290. Min Act: -0.1700
Data Index: 440435 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8290. Min Act: -0.1700
Data Index: 5108779 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.8290. Min Act: -0.1700
Data Index: 8053923 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7978. Min Act: -0.1700
Data Index: 378443 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7978. Min Act: -0.1700
Data Index: 8218613 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7978. Min Act: -0.1700
Data Index: 8053924 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7978. Min Act: -0.1700
Data Index: 2152928 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7978. Min Act: -0.1700
Data Index: 5321750 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7978. Min Act: -0.1700
Data Index: 1962982 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7978. Min Act: -0.1700
Data Index: 40181 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7978. Min Act: -0.1700
Data Index: 6853410 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7665. Min Act: -0.1700
Data Index: 283796 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8915. Min Range: -4.8915
Max Act: 4.7665. Min Act: -0.1700
Data Index: 6331677 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19