Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.5096. Min Act: -0.1700
Data Index: 1260549 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.4934. Min Act: -0.1700
Data Index: 7071029 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.4609. Min Act: -0.1700
Data Index: 5162686 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.4609. Min Act: -0.1700
Data Index: 3584957 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.4284. Min Act: -0.1700
Data Index: 3315937 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.4121. Min Act: -0.1700
Data Index: 6381859 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3958. Min Act: -0.1700
Data Index: 6707222 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.4121. Min Act: -0.1700
Data Index: 3113000 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3958. Min Act: -0.1700
Data Index: 7304697 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3958. Min Act: -0.1700
Data Index: 5122600 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3958. Min Act: -0.1695
Data Index: 2107642 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3958. Min Act: -0.1700
Data Index: 8145447 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.4121. Min Act: -0.1700
Data Index: 4926154 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3958. Min Act: -0.1700
Data Index: 5952280 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3958. Min Act: -0.1700
Data Index: 5221044 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3958. Min Act: -0.1700
Data Index: 2871277 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3958. Min Act: -0.1700
Data Index: 3759342 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3794. Min Act: -0.1700
Data Index: 3145793 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3794. Min Act: -0.1700
Data Index: 5042575 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5096. Min Range: -2.5096
Max Act: 2.3794. Min Act: -0.1700
Data Index: 281154 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19