Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1089 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.6026. Min Act: -0.1700
Data Index: 8757783 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.5704. Min Act: -0.1700
Data Index: 5955309 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.5543. Min Act: -0.1700
Data Index: 4702875 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.5058. Min Act: -0.1700
Data Index: 7150494 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4734. Min Act: -0.1700
Data Index: 8059422 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4734. Min Act: -0.1700
Data Index: 8297494 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4734. Min Act: -0.1700
Data Index: 5626335 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4571. Min Act: -0.1700
Data Index: 1293314 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4409. Min Act: -0.1700
Data Index: 1722800 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4571. Min Act: -0.1700
Data Index: 1293310 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4409. Min Act: -0.1700
Data Index: 5039387 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4409. Min Act: -0.1700
Data Index: 6374890 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4409. Min Act: -0.1700
Data Index: 7566398 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4246. Min Act: -0.1700
Data Index: 7259954 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4083. Min Act: -0.1700
Data Index: 2150152 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4246. Min Act: -0.1700
Data Index: 3304225 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4083. Min Act: -0.1700
Data Index: 8432753 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.4246. Min Act: -0.1700
Data Index: 5955311 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.3920. Min Act: -0.1700
Data Index: 4127113 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6026. Min Range: -2.6026
Max Act: 2.3756. Min Act: -0.1700
Data Index: 2316230 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19