Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5064. Min Range: -8.5064
Max Act: 8.5064. Min Act: -0.1700
Data Index: 2929544 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5064. Min Range: -8.5064
Max Act: 8.3814. Min Act: -0.1700
Data Index: 3656360 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5064. Min Range: -8.5064
Max Act: 8.0689. Min Act: -0.1700
Data Index: 2220524 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5064. Min Range: -8.5064
Max Act: 8.0377. Min Act: -0.1700
Data Index: 354439 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5064. Min Range: -8.5064
Max Act: 8.0064. Min Act: -0.1700
Data Index: 5951197 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.9439. Min Act: -0.1700
Data Index: 3315151 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.9127. Min Act: -0.1700
Data Index: 3675110 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.9439. Min Act: -0.1700
Data Index: 2598811 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.7564. Min Act: -0.1700
Data Index: 2094471 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.8189. Min Act: -0.1700
Data Index: 7544325 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.7564. Min Act: -0.1700
Data Index: 5373852 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.7252. Min Act: -0.1700
Data Index: 2892438 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.7564. Min Act: -0.1700
Data Index: 3791420 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.7564. Min Act: -0.1700
Data Index: 2029583 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.7252. Min Act: -0.1700
Data Index: 962193 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.6939. Min Act: -0.1700
Data Index: 2220523 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.6939. Min Act: -0.1700
Data Index: 8416247 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.6939. Min Act: -0.1700
Data Index: 2159942 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.6627. Min Act: -0.1700
Data Index: 1957359 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5064. Min Range: -8.5064
Max Act: 7.6627. Min Act: -0.1700
Data Index: 6383586 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19