Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4959 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2450. Min Range: -8.2450
Max Act: 8.2450. Min Act: -0.1700
Data Index: 6020679 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.9950. Min Act: -0.1700
Data Index: 6770058 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.9637. Min Act: -0.1700
Data Index: 3809396 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.8700. Min Act: -0.1700
Data Index: 515639 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.8700. Min Act: -0.1700
Data Index: 6033850 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.8387. Min Act: -0.1700
Data Index: 6734613 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.8387. Min Act: -0.1700
Data Index: 4627307 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.7762. Min Act: -0.1700
Data Index: 5994967 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.7450. Min Act: -0.1700
Data Index: 6300204 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.7762. Min Act: -0.1700
Data Index: 7885899 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.7450. Min Act: -0.1700
Data Index: 5934140 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.7137. Min Act: -0.1700
Data Index: 7123540 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.7450. Min Act: -0.1700
Data Index: 2485483 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.6825. Min Act: -0.1700
Data Index: 1414633 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.6825. Min Act: -0.1700
Data Index: 294369 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.6825. Min Act: -0.1700
Data Index: 6781445 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.6200. Min Act: -0.1700
Data Index: 2657298 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.6512. Min Act: -0.1700
Data Index: 151558 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.6200. Min Act: -0.1700
Data Index: 3264533 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2450. Min Range: -8.2450
Max Act: 6.6512. Min Act: -0.1700
Data Index: 4329995 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19