Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.2882. Min Act: -0.1700
Data Index: 7478632 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.2257. Min Act: -0.1700
Data Index: 6898165 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1945. Min Act: -0.1700
Data Index: 6789546 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1945. Min Act: -0.1700
Data Index: 6403928 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1632. Min Act: -0.1700
Data Index: 4114710 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1632. Min Act: -0.1700
Data Index: 3733386 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1632. Min Act: -0.1700
Data Index: 7782083 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1320. Min Act: -0.1700
Data Index: 8401060 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1320. Min Act: -0.1700
Data Index: 1312857 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1320. Min Act: -0.1700
Data Index: 2902730 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1320. Min Act: -0.1700
Data Index: 7782082 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1320. Min Act: -0.1700
Data Index: 1852645 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1320. Min Act: -0.1700
Data Index: 7782092 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1007. Min Act: -0.1700
Data Index: 7209435 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1007. Min Act: -0.1700
Data Index: 5137725 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1007. Min Act: -0.1700
Data Index: 5392289 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1007. Min Act: -0.1700
Data Index: 3025409 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1007. Min Act: -0.1700
Data Index: 7782091 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1007. Min Act: -0.1700
Data Index: 8078480 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2882. Min Range: -4.2882
Max Act: 4.1007. Min Act: -0.1700
Data Index: 6374435 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19