Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4955 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.4607. Min Act: -0.1700
Data Index: 2721358 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.3670. Min Act: -0.1700
Data Index: 4256045 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.1795. Min Act: -0.1700
Data Index: 143019 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.1482. Min Act: -0.1700
Data Index: 2006358 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.1482. Min Act: -0.1700
Data Index: 3275114 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.1482. Min Act: -0.1700
Data Index: 3275116 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.1170. Min Act: -0.1700
Data Index: 2363401 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.1170. Min Act: -0.1700
Data Index: 2584081 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.1170. Min Act: -0.1700
Data Index: 4559419 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0857. Min Act: -0.1700
Data Index: 6201217 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0545. Min Act: -0.1700
Data Index: 8281535 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0545. Min Act: -0.1700
Data Index: 3558798 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0232. Min Act: -0.1700
Data Index: 2810289 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0545. Min Act: -0.1700
Data Index: 5425409 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0545. Min Act: -0.1700
Data Index: 1441051 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0545. Min Act: -0.1700
Data Index: 8198725 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0232. Min Act: -0.1700
Data Index: 6238078 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0232. Min Act: -0.1700
Data Index: 139416 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0232. Min Act: -0.1700
Data Index: 4725906 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4607. Min Range: -5.4607
Max Act: 5.0232. Min Act: -0.1700
Data Index: 8198700 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19