Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.9499. Min Act: -0.1700
Data Index: 7553708 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.9187. Min Act: -0.1700
Data Index: 1840802 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.9187. Min Act: -0.1700
Data Index: 7702690 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.8562. Min Act: -0.1700
Data Index: 5099731 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.7937. Min Act: -0.1700
Data Index: 633791 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.8249. Min Act: -0.1700
Data Index: 4197497 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6687. Min Act: -0.1700
Data Index: 2798018 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.8249. Min Act: -0.1700
Data Index: 7636352 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.7624. Min Act: -0.1700
Data Index: 5167477 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.7312. Min Act: -0.1700
Data Index: 7907605 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6374. Min Act: -0.1700
Data Index: 7889599 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6999. Min Act: -0.1700
Data Index: 5561937 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6374. Min Act: -0.1700
Data Index: 2698185 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6999. Min Act: -0.1700
Data Index: 2062638 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6999. Min Act: -0.1700
Data Index: 518089 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6687. Min Act: -0.1700
Data Index: 3201449 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6999. Min Act: -0.1700
Data Index: 1628879 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6687. Min Act: -0.1700
Data Index: 921534 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6687. Min Act: -0.1700
Data Index: 3760395 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9499. Min Range: -5.9499
Max Act: 5.6374. Min Act: -0.1700
Data Index: 3536701 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19