Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0082. Min Range: -3.0082
Max Act: 3.0082. Min Act: -0.1700
Data Index: 2084264 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0082. Min Range: -3.0082
Max Act: 3.0082. Min Act: -0.1700
Data Index: 4754283 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.9608. Min Act: -0.1700
Data Index: 563863 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.9291. Min Act: -0.1700
Data Index: 1280917 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.9291. Min Act: -0.1700
Data Index: 6240020 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8816. Min Act: -0.1700
Data Index: 1428785 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8816. Min Act: -0.1700
Data Index: 4802746 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8816. Min Act: -0.1700
Data Index: 2453373 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8816. Min Act: -0.1700
Data Index: 2381109 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8339. Min Act: -0.1700
Data Index: 3243706 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8498. Min Act: -0.1700
Data Index: 4935501 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8180. Min Act: -0.1700
Data Index: 2978865 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8180. Min Act: -0.1700
Data Index: 4212039 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8498. Min Act: -0.1700
Data Index: 6850238 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.7702. Min Act: -0.1700
Data Index: 5959182 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.7862. Min Act: -0.1700
Data Index: 3006581 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8021. Min Act: -0.1700
Data Index: 6260077 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.7702. Min Act: -0.1700
Data Index: 4263034 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8021. Min Act: -0.1700
Data Index: 6522277 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0082. Min Range: -3.0082
Max Act: 2.8021. Min Act: -0.1700
Data Index: 4533773 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19