Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1788 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0582. Min Range: -3.0582
Max Act: 3.0582. Min Act: -0.1700
Data Index: 6315986 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9950. Min Act: -0.1700
Data Index: 2920399 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9792. Min Act: -0.1700
Data Index: 3868979 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0582. Min Range: -3.0582
Max Act: 3.0108. Min Act: -0.1700
Data Index: 6990184 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9634. Min Act: -0.1700
Data Index: 6537364 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9317. Min Act: -0.1700
Data Index: 1785351 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9475. Min Act: -0.1700
Data Index: 1310880 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9475. Min Act: -0.1700
Data Index: 7040955 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9792. Min Act: -0.1700
Data Index: 8127104 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9634. Min Act: -0.1700
Data Index: 3714199 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9634. Min Act: -0.1700
Data Index: 771123 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9475. Min Act: -0.1700
Data Index: 4149375 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9317. Min Act: -0.1700
Data Index: 5742722 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9317. Min Act: -0.1700
Data Index: 3744492 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9317. Min Act: -0.1700
Data Index: 5309786 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9159. Min Act: -0.1700
Data Index: 108874 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9159. Min Act: -0.1700
Data Index: 8531034 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9317. Min Act: -0.1700
Data Index: 2690791 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9159. Min Act: -0.1700
Data Index: 3590473 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0582. Min Range: -3.0582
Max Act: 2.9317. Min Act: -0.1700
Data Index: 8019589 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19