Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4558 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2784. Min Range: -4.2784
Max Act: 4.2784. Min Act: -0.1700
Data Index: 2291921 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2784. Min Range: -4.2784
Max Act: 4.2784. Min Act: -0.1700
Data Index: 1035295 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2784. Min Range: -4.2784
Max Act: 4.1221. Min Act: -0.1700
Data Index: 6091601 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2784. Min Range: -4.2784
Max Act: 4.0908. Min Act: -0.1700
Data Index: 8246306 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2784. Min Range: -4.2784
Max Act: 4.0596. Min Act: -0.1700
Data Index: 6905090 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2784. Min Range: -4.2784
Max Act: 4.0283. Min Act: -0.1700
Data Index: 6683354 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.9971. Min Act: -0.1700
Data Index: 6258434 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.9658. Min Act: -0.1700
Data Index: 2303520 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.9189. Min Act: -0.1700
Data Index: 6906619 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.9033. Min Act: -0.1700
Data Index: 4406767 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.8720. Min Act: -0.1700
Data Index: 4438695 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.9033. Min Act: -0.1700
Data Index: 7419116 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.8876. Min Act: -0.1700
Data Index: 2158288 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.8407. Min Act: -0.1700
Data Index: 4570690 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.8564. Min Act: -0.1700
Data Index: 6830613 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.8095. Min Act: -0.1700
Data Index: 2676757 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.7938. Min Act: -0.1700
Data Index: 6906620 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.7625. Min Act: -0.1700
Data Index: 2207374 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.7938. Min Act: -0.1700
Data Index: 461373 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2784. Min Range: -4.2784
Max Act: 3.7625. Min Act: -0.1700
Data Index: 166339 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19