Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2125. Min Range: -5.2125
Max Act: 5.1813. Min Act: -0.1700
Data Index: 1051836 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2125. Min Range: -5.2125
Max Act: 5.2125. Min Act: -0.1700
Data Index: 4278400 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.9313. Min Act: -0.1700
Data Index: 3021179 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.8375. Min Act: -0.1700
Data Index: 3350391 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.8375. Min Act: -0.1700
Data Index: 8486550 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.7750. Min Act: -0.1700
Data Index: 5771119 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.7750. Min Act: -0.1700
Data Index: 6438418 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.7125. Min Act: -0.1700
Data Index: 2422259 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.6813. Min Act: -0.1700
Data Index: 7647697 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.6813. Min Act: -0.1700
Data Index: 5093314 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.6500. Min Act: -0.1700
Data Index: 3866673 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.6500. Min Act: -0.1700
Data Index: 7573942 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.6500. Min Act: -0.1700
Data Index: 3109010 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.6188. Min Act: -0.1700
Data Index: 3715653 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.5875. Min Act: -0.1700
Data Index: 3715670 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.6188. Min Act: -0.1700
Data Index: 8112675 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.5875. Min Act: -0.1700
Data Index: 1762252 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.5875. Min Act: -0.1700
Data Index: 3770899 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.5250. Min Act: -0.1700
Data Index: 8414699 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2125. Min Range: -5.2125
Max Act: 4.5563. Min Act: -0.1700
Data Index: 8032374 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19