Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1040 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.6487. Min Act: -0.1700
Data Index: 7882019 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.3049. Min Act: -0.1700
Data Index: 3102478 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.2737. Min Act: -0.1700
Data Index: 2675273 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.1799. Min Act: -0.1700
Data Index: 2487100 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.1799. Min Act: -0.1700
Data Index: 305336 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.1799. Min Act: -0.1700
Data Index: 5572002 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.1174. Min Act: -0.1700
Data Index: 8686096 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.1174. Min Act: -0.1700
Data Index: 993296 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0862. Min Act: -0.1700
Data Index: 8797418 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0237. Min Act: -0.1700
Data Index: 5878305 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0549. Min Act: -0.1700
Data Index: 4984436 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0549. Min Act: -0.1700
Data Index: 723051 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0862. Min Act: -0.1700
Data Index: 1192756 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0862. Min Act: -0.1700
Data Index: 3219614 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0549. Min Act: -0.1700
Data Index: 2030147 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0237. Min Act: -0.1700
Data Index: 1715468 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0549. Min Act: -0.1700
Data Index: 8018036 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0549. Min Act: -0.1700
Data Index: 3161158 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6487. Min Range: -5.6487
Max Act: 4.9924. Min Act: -0.1700
Data Index: 6795039 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6487. Min Range: -5.6487
Max Act: 5.0862. Min Act: -0.1700
Data Index: 7338726 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19