Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2102 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.9519. Min Act: -0.1700
Data Index: 7879657 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.9831. Min Act: -0.1700
Data Index: 5209523 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.7331. Min Act: -0.1700
Data Index: 7498184 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.7331. Min Act: -0.1700
Data Index: 823015 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.6706. Min Act: -0.1700
Data Index: 3627065 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.6081. Min Act: -0.1700
Data Index: 776967 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.5769. Min Act: -0.1700
Data Index: 8397629 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.5144. Min Act: -0.1700
Data Index: 8067363 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4519. Min Act: -0.1700
Data Index: 765631 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4831. Min Act: -0.1700
Data Index: 243971 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4831. Min Act: -0.1700
Data Index: 1732390 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.5144. Min Act: -0.1700
Data Index: 2425285 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4519. Min Act: -0.1700
Data Index: 2825618 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4519. Min Act: -0.1700
Data Index: 592360 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4519. Min Act: -0.1700
Data Index: 1520851 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4519. Min Act: -0.1700
Data Index: 2129483 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4519. Min Act: -0.1700
Data Index: 333124 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4206. Min Act: -0.1700
Data Index: 1623919 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4519. Min Act: -0.1700
Data Index: 3275122 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9831. Min Range: -5.9831
Max Act: 5.4206. Min Act: -0.1700
Data Index: 3176679 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19