Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4325. Min Act: -0.1700
Data Index: 2593734 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.4325. Min Act: -0.1700
Data Index: 4909594 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3700. Min Act: -0.1700
Data Index: 901064 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3388. Min Act: -0.1700
Data Index: 4261359 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3075. Min Act: -0.1700
Data Index: 4028761 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.3075. Min Act: -0.1700
Data Index: 8556533 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2763. Min Act: -0.1700
Data Index: 8728901 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2763. Min Act: -0.1700
Data Index: 5080495 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2763. Min Act: -0.1700
Data Index: 3547683 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2450. Min Act: -0.1700
Data Index: 3800373 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2450. Min Act: -0.1700
Data Index: 7333496 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2450. Min Act: -0.1700
Data Index: 6335856 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2450. Min Act: -0.1700
Data Index: 6245701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2138. Min Act: -0.1700
Data Index: 7102540 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2138. Min Act: -0.1700
Data Index: 6669763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2138. Min Act: -0.1700
Data Index: 411448 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2138. Min Act: -0.1700
Data Index: 6482541 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2138. Min Act: -0.1700
Data Index: 631760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2138. Min Act: -0.1700
Data Index: 3678742 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4325. Min Range: -4.4325
Max Act: 4.2138. Min Act: -0.1700
Data Index: 4878191 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19