Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1553 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.3553. Min Act: -0.1700
Data Index: 7604220 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.3553. Min Act: -0.1700
Data Index: 3931616 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.3225. Min Act: -0.1700
Data Index: 8732838 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.3225. Min Act: -0.1700
Data Index: 2894658 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2896. Min Act: -0.1700
Data Index: 4265893 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2896. Min Act: -0.1700
Data Index: 8546992 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2731. Min Act: -0.1700
Data Index: 7869443 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2566. Min Act: -0.1700
Data Index: 3286670 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2236. Min Act: -0.1700
Data Index: 7402663 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2236. Min Act: -0.1700
Data Index: 8544487 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2236. Min Act: -0.1700
Data Index: 2953216 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2236. Min Act: -0.1700
Data Index: 366118 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2401. Min Act: -0.1700
Data Index: 1112697 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2070. Min Act: -0.1700
Data Index: 6337680 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2070. Min Act: -0.1700
Data Index: 2482290 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.2070. Min Act: -0.1700
Data Index: 8807461 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.1904. Min Act: -0.1700
Data Index: 5195965 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.1904. Min Act: -0.1700
Data Index: 7485954 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.1738. Min Act: -0.1700
Data Index: 4617150 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3553. Min Range: -2.3553
Max Act: 2.1738. Min Act: -0.1700
Data Index: 395339 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19