Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.9389. Min Act: -0.1700
Data Index: 5794311 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.9389. Min Act: -0.1700
Data Index: 7723235 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.9076. Min Act: -0.1700
Data Index: 6654879 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.9076. Min Act: -0.1700
Data Index: 6941790 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.9389. Min Act: -0.1700
Data Index: 1615689 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.8764. Min Act: -0.1700
Data Index: 6045051 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.8451. Min Act: -0.1700
Data Index: 2888862 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.8451. Min Act: -0.1700
Data Index: 5647284 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.7826. Min Act: -0.1700
Data Index: 2091525 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.7826. Min Act: -0.1700
Data Index: 5700835 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.7514. Min Act: -0.1700
Data Index: 310203 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.7514. Min Act: -0.1700
Data Index: 7413365 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.7514. Min Act: -0.1700
Data Index: 653825 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.7514. Min Act: -0.1700
Data Index: 8349775 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.7201. Min Act: -0.1700
Data Index: 3798841 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.6889. Min Act: -0.1700
Data Index: 854566 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.6889. Min Act: -0.1700
Data Index: 8074386 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.6889. Min Act: -0.1700
Data Index: 8278574 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.6576. Min Act: -0.1700
Data Index: 4744699 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9389. Min Range: -4.9389
Max Act: 4.6576. Min Act: -0.1700
Data Index: 1269624 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19