Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5448. Min Range: -6.5448
Max Act: 6.5448. Min Act: -0.1700
Data Index: 314943 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5448. Min Range: -6.5448
Max Act: 6.3886. Min Act: -0.1700
Data Index: 8696356 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5448. Min Range: -6.5448
Max Act: 6.3886. Min Act: -0.1700
Data Index: 4885752 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5448. Min Range: -6.5448
Max Act: 6.1698. Min Act: -0.1700
Data Index: 3832390 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5448. Min Range: -6.5448
Max Act: 6.0761. Min Act: -0.1700
Data Index: 4530387 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5448. Min Range: -6.5448
Max Act: 6.0448. Min Act: -0.1700
Data Index: 5170513 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.9823. Min Act: -0.1700
Data Index: 107136 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.9198. Min Act: -0.1700
Data Index: 1933585 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.8886. Min Act: -0.1700
Data Index: 8478480 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.8886. Min Act: -0.1700
Data Index: 8753088 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.8886. Min Act: -0.1700
Data Index: 6359051 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.8573. Min Act: -0.1700
Data Index: 1963175 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.8886. Min Act: -0.1700
Data Index: 4850684 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.8573. Min Act: -0.1700
Data Index: 11005 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.8261. Min Act: -0.1700
Data Index: 6768098 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.8573. Min Act: -0.1700
Data Index: 1393566 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.7948. Min Act: -0.1700
Data Index: 4890947 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.7636. Min Act: -0.1700
Data Index: 3844460 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.7636. Min Act: -0.1700
Data Index: 955754 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5448. Min Range: -6.5448
Max Act: 5.7636. Min Act: -0.1700
Data Index: 6760266 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19