Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4721 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.5031. Min Act: -0.1700
Data Index: 94666 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.5031. Min Act: -0.1700
Data Index: 8356896 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.5031. Min Act: -0.1700
Data Index: 7334408 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.4718. Min Act: -0.1700
Data Index: 8260334 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.3781. Min Act: -0.1700
Data Index: 8175670 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.4093. Min Act: -0.1700
Data Index: 7273941 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.2218. Min Act: -0.1700
Data Index: 7743506 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.1906. Min Act: -0.1700
Data Index: 3007685 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.1593. Min Act: -0.1700
Data Index: 3007683 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.1593. Min Act: -0.1700
Data Index: 6808211 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.1281. Min Act: -0.1700
Data Index: 7663256 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.1281. Min Act: -0.1700
Data Index: 543538 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.0968. Min Act: -0.1700
Data Index: 1528545 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.0968. Min Act: -0.1700
Data Index: 870553 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.0968. Min Act: -0.1700
Data Index: 4042943 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.0968. Min Act: -0.1700
Data Index: 3921625 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.0656. Min Act: -0.1700
Data Index: 7442059 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.0656. Min Act: -0.1700
Data Index: 2159654 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.0656. Min Act: -0.1700
Data Index: 3940010 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5031. Min Range: -4.5031
Max Act: 4.0656. Min Act: -0.1700
Data Index: 65424 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19