Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.6489. Min Act: -0.1700
Data Index: 6865001 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.6489. Min Act: -0.1700
Data Index: 3753728 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.5239. Min Act: -0.1700
Data Index: 2811880 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4927. Min Act: -0.1700
Data Index: 4577469 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4927. Min Act: -0.1700
Data Index: 6583338 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4614. Min Act: -0.1700
Data Index: 48219 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4614. Min Act: -0.1700
Data Index: 2033662 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4927. Min Act: -0.1700
Data Index: 4638685 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.4614. Min Act: -0.1700
Data Index: 6412933 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3677. Min Act: -0.1700
Data Index: 5430341 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3677. Min Act: -0.1700
Data Index: 1654580 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3677. Min Act: -0.1700
Data Index: 7024766 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3677. Min Act: -0.1700
Data Index: 2346081 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3677. Min Act: -0.1700
Data Index: 7842176 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3677. Min Act: -0.1700
Data Index: 6722801 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3364. Min Act: -0.1700
Data Index: 5193958 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3364. Min Act: -0.1700
Data Index: 7526378 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3052. Min Act: -0.1700
Data Index: 6994101 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3052. Min Act: -0.1700
Data Index: 7218306 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6489. Min Range: -6.6489
Max Act: 6.3052. Min Act: -0.1700
Data Index: 7761806 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19