Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5053 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0555. Min Range: -2.0555
Max Act: 2.0555. Min Act: -0.1700
Data Index: 3992636 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0555. Min Range: -2.0555
Max Act: 2.0386. Min Act: -0.1699
Data Index: 7828042 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0555. Min Range: -2.0555
Max Act: 2.0218. Min Act: -0.1700
Data Index: 8574831 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.9541. Min Act: -0.1699
Data Index: 5126439 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.9201. Min Act: -0.1699
Data Index: 7250273 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8860. Min Act: -0.1700
Data Index: 4325567 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.9031. Min Act: -0.1700
Data Index: 4015098 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8689. Min Act: -0.1700
Data Index: 3921041 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.9031. Min Act: -0.1700
Data Index: 2866381 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8689. Min Act: -0.1698
Data Index: 3372254 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8347. Min Act: -0.1700
Data Index: 1552440 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8175. Min Act: -0.1700
Data Index: 5284955 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8175. Min Act: -0.1700
Data Index: 2730803 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8175. Min Act: -0.1700
Data Index: 1083965 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8175. Min Act: -0.1700
Data Index: 5626511 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8175. Min Act: -0.1700
Data Index: 3277803 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8003. Min Act: -0.1698
Data Index: 6823809 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.7831. Min Act: -0.1690
Data Index: 6909595 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8003. Min Act: -0.1700
Data Index: 786823 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0555. Min Range: -2.0555
Max Act: 1.8003. Min Act: -0.1700
Data Index: 385905 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19