Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.7461. Min Act: -0.1700
Data Index: 294086 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.5427. Min Act: -0.1700
Data Index: 445136 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.4644. Min Act: -0.1700
Data Index: 1967654 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.4644. Min Act: -0.1700
Data Index: 1129117 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.4331. Min Act: -0.1700
Data Index: 8445378 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.4331. Min Act: -0.1700
Data Index: 6331556 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.4487. Min Act: -0.1700
Data Index: 5522707 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3860. Min Act: -0.1700
Data Index: 2663640 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3704. Min Act: -0.1700
Data Index: 6749695 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3704. Min Act: -0.1700
Data Index: 7790944 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3547. Min Act: -0.1700
Data Index: 7043914 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3704. Min Act: -0.1700
Data Index: 4599190 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3547. Min Act: -0.1700
Data Index: 3476948 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3704. Min Act: -0.1700
Data Index: 1767482 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3704. Min Act: -0.1700
Data Index: 3642872 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3233. Min Act: -0.1700
Data Index: 8393182 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3076. Min Act: -0.1700
Data Index: 4492851 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3390. Min Act: -0.1700
Data Index: 4169120 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3390. Min Act: -0.1700
Data Index: 652974 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7461. Min Range: -3.7461
Max Act: 3.3233. Min Act: -0.1700
Data Index: 2625703 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19