Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3820 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0059. Min Range: -5.0059
Max Act: 5.0059. Min Act: -0.1700
Data Index: 5427089 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0059. Min Range: -5.0059
Max Act: 5.0059. Min Act: -0.1700
Data Index: 2012952 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.5996. Min Act: -0.1700
Data Index: 6610443 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.6621. Min Act: -0.1700
Data Index: 5573087 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.5996. Min Act: -0.1700
Data Index: 1918369 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.5996. Min Act: -0.1700
Data Index: 1222633 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.4746. Min Act: -0.1700
Data Index: 1580702 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.4746. Min Act: -0.1700
Data Index: 7256734 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.5059. Min Act: -0.1700
Data Index: 8476518 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.4746. Min Act: -0.1700
Data Index: 1969228 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.4121. Min Act: -0.1700
Data Index: 4980 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.4434. Min Act: -0.1700
Data Index: 1918368 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.3809. Min Act: -0.1700
Data Index: 1198192 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.3184. Min Act: -0.1700
Data Index: 7920119 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.3809. Min Act: -0.1700
Data Index: 1194204 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.3184. Min Act: -0.1700
Data Index: 6815902 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.3496. Min Act: -0.1700
Data Index: 2792313 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.3184. Min Act: -0.1700
Data Index: 7302961 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.3184. Min Act: -0.1700
Data Index: 5796847 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0059. Min Range: -5.0059
Max Act: 4.3184. Min Act: -0.1700
Data Index: 2146714 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19