Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0382. Min Range: -7.0382
Max Act: 7.0382. Min Act: -0.1700
Data Index: 3842841 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0382. Min Range: -7.0382
Max Act: 7.0382. Min Act: -0.1700
Data Index: 7951626 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.9132. Min Act: -0.1700
Data Index: 8199275 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.9132. Min Act: -0.1700
Data Index: 8522205 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.8195. Min Act: -0.1700
Data Index: 4002969 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.8507. Min Act: -0.1700
Data Index: 5671685 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.8507. Min Act: -0.1700
Data Index: 845372 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.8195. Min Act: -0.1700
Data Index: 5369615 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.7882. Min Act: -0.1700
Data Index: 4920693 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.7882. Min Act: -0.1700
Data Index: 4359875 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.7570. Min Act: -0.1700
Data Index: 6302309 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.7570. Min Act: -0.1700
Data Index: 7587494 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.7570. Min Act: -0.1700
Data Index: 2335989 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.6945. Min Act: -0.1700
Data Index: 8401347 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.6945. Min Act: -0.1700
Data Index: 3344438 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.6945. Min Act: -0.1700
Data Index: 3388164 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.6320. Min Act: -0.1700
Data Index: 7517978 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.6632. Min Act: -0.1699
Data Index: 7593683 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.6007. Min Act: -0.1700
Data Index: 4343307 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0382. Min Range: -7.0382
Max Act: 6.6320. Min Act: -0.1700
Data Index: 3416939 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19