Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1837 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.3498. Min Act: -0.1700
Data Index: 6756168 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.3498. Min Act: -0.1700
Data Index: 4028721 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.2556. Min Act: -0.1700
Data Index: 6038222 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.2085. Min Act: -0.1700
Data Index: 645606 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.2242. Min Act: -0.1700
Data Index: 353496 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.1770. Min Act: -0.1700
Data Index: 7769411 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.1613. Min Act: -0.1700
Data Index: 6694152 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.1140. Min Act: -0.1700
Data Index: 1189588 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.1298. Min Act: -0.1700
Data Index: 5534639 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.1298. Min Act: -0.1700
Data Index: 3583958 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.1140. Min Act: -0.1700
Data Index: 1401377 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.0825. Min Act: -0.1700
Data Index: 4090473 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.0667. Min Act: -0.1700
Data Index: 6566864 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.0983. Min Act: -0.1700
Data Index: 7515089 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.0667. Min Act: -0.1700
Data Index: 1532329 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.0667. Min Act: -0.1700
Data Index: 3629976 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.0667. Min Act: -0.1700
Data Index: 6778643 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.0667. Min Act: -0.1700
Data Index: 124811 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.0667. Min Act: -0.1700
Data Index: 2639627 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3498. Min Range: -3.3498
Max Act: 3.0667. Min Act: -0.1700
Data Index: 176446 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19