Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1895. Min Range: -3.1895
Max Act: 3.1895. Min Act: -0.1700
Data Index: 7453095 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1895. Min Range: -3.1895
Max Act: 3.0477. Min Act: -0.1700
Data Index: 7005266 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9845. Min Act: -0.1700
Data Index: 186182 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1895. Min Range: -3.1895
Max Act: 3.0003. Min Act: -0.1700
Data Index: 8810815 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9845. Min Act: -0.1700
Data Index: 6945989 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9687. Min Act: -0.1700
Data Index: 1533277 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9371. Min Act: -0.1700
Data Index: 410986 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9371. Min Act: -0.1700
Data Index: 8256681 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9212. Min Act: -0.1700
Data Index: 4189121 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9371. Min Act: -0.1700
Data Index: 1591332 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9212. Min Act: -0.1700
Data Index: 2187487 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9212. Min Act: -0.1700
Data Index: 8699712 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9054. Min Act: -0.1700
Data Index: 1307314 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9054. Min Act: -0.1700
Data Index: 2261149 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.9054. Min Act: -0.1700
Data Index: 2623124 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.8895. Min Act: -0.1700
Data Index: 2663840 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.8736. Min Act: -0.1700
Data Index: 4831069 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.8736. Min Act: -0.1700
Data Index: 5670868 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.8578. Min Act: -0.1700
Data Index: 5589479 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1895. Min Range: -3.1895
Max Act: 2.8736. Min Act: -0.1700
Data Index: 1026019 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19