Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5255 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.3619. Min Act: -0.1700
Data Index: 4726762 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.3619. Min Act: -0.1700
Data Index: 6308187 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2994. Min Act: -0.1700
Data Index: 6507798 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2369. Min Act: -0.1700
Data Index: 369905 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2056. Min Act: -0.1700
Data Index: 6872077 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.2056. Min Act: -0.1700
Data Index: 5602657 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1744. Min Act: -0.1700
Data Index: 6535148 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1744. Min Act: -0.1700
Data Index: 1929675 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1744. Min Act: -0.1700
Data Index: 7783493 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1119. Min Act: -0.1700
Data Index: 198849 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1431. Min Act: -0.1700
Data Index: 356403 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.1431. Min Act: -0.1700
Data Index: 8799259 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 6742108 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 3159603 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 5235837 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 5077644 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 4801103 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0806. Min Act: -0.1700
Data Index: 402966 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 5878195 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3619. Min Range: -5.3619
Max Act: 5.0494. Min Act: -0.1700
Data Index: 5977339 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19