Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1617. Min Range: -6.1617
Max Act: 6.1617. Min Act: -0.1700
Data Index: 1744301 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1617. Min Range: -6.1617
Max Act: 6.0992. Min Act: -0.1700
Data Index: 1826890 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1617. Min Range: -6.1617
Max Act: 6.0992. Min Act: -0.1700
Data Index: 8749146 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1617. Min Range: -6.1617
Max Act: 6.0367. Min Act: -0.1700
Data Index: 8142956 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1617. Min Range: -6.1617
Max Act: 6.0054. Min Act: -0.1700
Data Index: 2099788 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.9742. Min Act: -0.1700
Data Index: 562396 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.9742. Min Act: -0.1700
Data Index: 8464246 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.9429. Min Act: -0.1700
Data Index: 461982 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.9117. Min Act: -0.1700
Data Index: 5567987 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.8804. Min Act: -0.1700
Data Index: 3808683 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.9117. Min Act: -0.1700
Data Index: 8318237 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.9117. Min Act: -0.1700
Data Index: 3292778 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.8804. Min Act: -0.1700
Data Index: 5579532 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.8492. Min Act: -0.1700
Data Index: 8586906 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.8492. Min Act: -0.1700
Data Index: 6362060 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.8492. Min Act: -0.1700
Data Index: 7854910 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.8492. Min Act: -0.1700
Data Index: 7653589 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.8492. Min Act: -0.1700
Data Index: 231574 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.8492. Min Act: -0.1700
Data Index: 7432964 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1617. Min Range: -6.1617
Max Act: 5.8179. Min Act: -0.1700
Data Index: 4702634 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19