Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.8051. Min Act: -0.1700
Data Index: 5308544 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.7891. Min Act: -0.1700
Data Index: 3297061 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.7093. Min Act: -0.1700
Data Index: 8798513 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.7253. Min Act: -0.1700
Data Index: 4875484 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.7413. Min Act: -0.1700
Data Index: 5219570 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.7572. Min Act: -0.1700
Data Index: 2802339 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.7093. Min Act: -0.1700
Data Index: 5274129 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.7093. Min Act: -0.1700
Data Index: 423981 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6933. Min Act: -0.1700
Data Index: 6289729 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6292. Min Act: -0.1700
Data Index: 674390 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6773. Min Act: -0.1700
Data Index: 8816328 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6292. Min Act: -0.1700
Data Index: 8356662 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6452. Min Act: -0.1700
Data Index: 7748093 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6292. Min Act: -0.1700
Data Index: 4403025 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6292. Min Act: -0.1700
Data Index: 372149 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6131. Min Act: -0.1700
Data Index: 4282865 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6292. Min Act: -0.1700
Data Index: 2948688 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6292. Min Act: -0.1700
Data Index: 7770756 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6131. Min Act: -0.1700
Data Index: 361992 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8051. Min Range: -2.8051
Max Act: 2.6452. Min Act: -0.1700
Data Index: 4307096 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19