Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.5555. Min Act: -0.1700
Data Index: 4810994 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.5070. Min Act: -0.1700
Data Index: 4111567 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4258. Min Act: -0.1700
Data Index: 5863274 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3932. Min Act: -0.1700
Data Index: 5417232 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3932. Min Act: -0.1700
Data Index: 4722356 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3768. Min Act: -0.1700
Data Index: 5607613 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3768. Min Act: -0.1700
Data Index: 5194541 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3932. Min Act: -0.1700
Data Index: 3158279 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3441. Min Act: -0.1700
Data Index: 3248165 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3605. Min Act: -0.1700
Data Index: 4737003 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3441. Min Act: -0.1700
Data Index: 2681067 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3441. Min Act: -0.1700
Data Index: 5462677 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3277. Min Act: -0.1700
Data Index: 5863275 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3277. Min Act: -0.1700
Data Index: 6040311 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3277. Min Act: -0.1700
Data Index: 6187585 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3277. Min Act: -0.1700
Data Index: 685754 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3441. Min Act: -0.1700
Data Index: 3846747 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3113. Min Act: -0.1700
Data Index: 468032 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3113. Min Act: -0.1700
Data Index: 340519 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.3113. Min Act: -0.1700
Data Index: 1454090 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19