Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.9555. Min Act: -0.1700
Data Index: 3077866 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.9243. Min Act: -0.1700
Data Index: 7373442 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.9243. Min Act: -0.1700
Data Index: 3271353 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.9243. Min Act: -0.1700
Data Index: 8733991 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.8305. Min Act: -0.1700
Data Index: 818637 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.8618. Min Act: -0.1700
Data Index: 4507077 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.8305. Min Act: -0.1700
Data Index: 6010020 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.8305. Min Act: -0.1700
Data Index: 6587048 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.8305. Min Act: -0.1700
Data Index: 3522252 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7993. Min Act: -0.1700
Data Index: 2944374 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7993. Min Act: -0.1700
Data Index: 247086 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.8305. Min Act: -0.1700
Data Index: 3454182 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7993. Min Act: -0.1700
Data Index: 8288776 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7993. Min Act: -0.1700
Data Index: 748746 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7680. Min Act: -0.1700
Data Index: 3595190 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7680. Min Act: -0.1700
Data Index: 6687040 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7680. Min Act: -0.1700
Data Index: 2293667 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7680. Min Act: -0.1700
Data Index: 2908225 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7680. Min Act: -0.1700
Data Index: 4372197 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9555. Min Range: -4.9555
Max Act: 4.7368. Min Act: -0.1700
Data Index: 18170 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19