Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.6281. Min Act: -0.1700
Data Index: 5318760 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.5656. Min Act: -0.1700
Data Index: 3962421 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.5968. Min Act: -0.1700
Data Index: 5130121 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.5656. Min Act: -0.1700
Data Index: 1196148 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.5343. Min Act: -0.1700
Data Index: 5756298 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.5031. Min Act: -0.1700
Data Index: 7377458 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.5031. Min Act: -0.1700
Data Index: 2398046 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.5031. Min Act: -0.1700
Data Index: 200547 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4718. Min Act: -0.1700
Data Index: 4750165 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4718. Min Act: -0.1700
Data Index: 5493221 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4406. Min Act: -0.1700
Data Index: 7415483 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4093. Min Act: -0.1700
Data Index: 905052 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4406. Min Act: -0.1700
Data Index: 3869967 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4406. Min Act: -0.1700
Data Index: 437619 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4406. Min Act: -0.1700
Data Index: 632730 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4093. Min Act: -0.1700
Data Index: 3962426 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4093. Min Act: -0.1700
Data Index: 4952257 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4093. Min Act: -0.1700
Data Index: 1263031 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4093. Min Act: -0.1700
Data Index: 5397016 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6281. Min Range: -4.6281
Max Act: 4.4093. Min Act: -0.1700
Data Index: 6766643 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19