Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1777. Min Range: -4.1777
Max Act: 4.1777. Min Act: -0.1700
Data Index: 327738 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1777. Min Range: -4.1777
Max Act: 4.1464. Min Act: -0.1700
Data Index: 4139521 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1777. Min Range: -4.1777
Max Act: 4.0526. Min Act: -0.1700
Data Index: 275929 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1777. Min Range: -4.1777
Max Act: 4.0839. Min Act: -0.1700
Data Index: 6990751 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1777. Min Range: -4.1777
Max Act: 4.0839. Min Act: -0.1700
Data Index: 8739287 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1777. Min Range: -4.1777
Max Act: 4.0214. Min Act: -0.1700
Data Index: 2556609 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1777. Min Range: -4.1777
Max Act: 4.0214. Min Act: -0.1700
Data Index: 2244506 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9901. Min Act: -0.1700
Data Index: 885375 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9901. Min Act: -0.1700
Data Index: 8739288 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9901. Min Act: -0.1700
Data Index: 275930 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9589. Min Act: -0.1700
Data Index: 1766260 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9589. Min Act: -0.1700
Data Index: 252139 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9589. Min Act: -0.1700
Data Index: 7866470 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9589. Min Act: -0.1700
Data Index: 3369307 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9589. Min Act: -0.1700
Data Index: 8530465 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9276. Min Act: -0.1700
Data Index: 2629635 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9276. Min Act: -0.1700
Data Index: 2568404 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9276. Min Act: -0.1700
Data Index: 252136 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.9276. Min Act: -0.1700
Data Index: 252138 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1777. Min Range: -4.1777
Max Act: 3.8963. Min Act: -0.1700
Data Index: 4833190 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19