Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5897 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.3573. Min Act: -0.1700
Data Index: 8169371 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.3416. Min Act: -0.1700
Data Index: 214492 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.3416. Min Act: -0.1700
Data Index: 4964531 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2474. Min Act: -0.1700
Data Index: 2015065 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2317. Min Act: -0.1700
Data Index: 2324428 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2160. Min Act: -0.1700
Data Index: 6544697 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2160. Min Act: -0.1700
Data Index: 1603679 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2002. Min Act: -0.1700
Data Index: 6427344 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1845. Min Act: -0.1700
Data Index: 8268171 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.2160. Min Act: -0.1700
Data Index: 8115047 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1845. Min Act: -0.1700
Data Index: 4088565 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1845. Min Act: -0.1700
Data Index: 6935678 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1688. Min Act: -0.1700
Data Index: 3730966 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1845. Min Act: -0.1700
Data Index: 3800654 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1688. Min Act: -0.1700
Data Index: 784429 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1530. Min Act: -0.1700
Data Index: 5784788 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1373. Min Act: -0.1700
Data Index: 677129 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1373. Min Act: -0.1700
Data Index: 1031764 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1373. Min Act: -0.1700
Data Index: 844596 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1216. Min Act: -0.1700
Data Index: 862194 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19