Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3964 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2670. Min Range: -6.2670
Max Act: 6.2670. Min Act: -0.1700
Data Index: 2724010 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2670. Min Range: -6.2670
Max Act: 6.1107. Min Act: -0.1700
Data Index: 1433230 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2670. Min Range: -6.2670
Max Act: 6.0795. Min Act: -0.1700
Data Index: 2247327 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2670. Min Range: -6.2670
Max Act: 6.0170. Min Act: -0.1700
Data Index: 3444250 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2670. Min Range: -6.2670
Max Act: 6.0170. Min Act: -0.1700
Data Index: 217713 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.9857. Min Act: -0.1700
Data Index: 2380405 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.9232. Min Act: -0.1700
Data Index: 4470326 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.9545. Min Act: -0.1700
Data Index: 8669693 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.9232. Min Act: -0.1700
Data Index: 6959077 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.8607. Min Act: -0.1700
Data Index: 701086 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.8607. Min Act: -0.1700
Data Index: 8587527 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.8607. Min Act: -0.1700
Data Index: 771577 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.8295. Min Act: -0.1700
Data Index: 1742853 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.8920. Min Act: -0.1700
Data Index: 8535149 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.8295. Min Act: -0.1700
Data Index: 6663477 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.8295. Min Act: -0.1700
Data Index: 5270449 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.7982. Min Act: -0.1700
Data Index: 806496 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.8607. Min Act: -0.1700
Data Index: 5373384 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.7670. Min Act: -0.1700
Data Index: 6586527 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2670. Min Range: -6.2670
Max Act: 5.7357. Min Act: -0.1700
Data Index: 3184872 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19