Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.9658. Min Act: -0.1700
Data Index: 5383581 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.4345. Min Act: -0.1700
Data Index: 570312 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.3095. Min Act: -0.1700
Data Index: 7951185 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.0595. Min Act: -0.1700
Data Index: 3924660 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9658. Min Range: -7.9658
Max Act: 7.0283. Min Act: -0.1700
Data Index: 7795457 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.9345. Min Act: -0.1700
Data Index: 6010770 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.8720. Min Act: -0.1700
Data Index: 5301668 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.7783. Min Act: -0.1700
Data Index: 3741745 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.8095. Min Act: -0.1700
Data Index: 948847 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.7783. Min Act: -0.1700
Data Index: 3614325 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.7158. Min Act: -0.1700
Data Index: 7466553 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.7158. Min Act: -0.1700
Data Index: 4289393 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.7158. Min Act: -0.1700
Data Index: 2346627 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.6845. Min Act: -0.1700
Data Index: 8120959 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.6533. Min Act: -0.1700
Data Index: 441465 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.6533. Min Act: -0.1700
Data Index: 1467967 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.6220. Min Act: -0.1700
Data Index: 4794084 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.6220. Min Act: -0.1700
Data Index: 5605134 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.6220. Min Act: -0.1700
Data Index: 2240051 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9658. Min Range: -7.9658
Max Act: 6.5908. Min Act: -0.1700
Data Index: 4128626 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19