Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2198. Min Range: -7.2198
Max Act: 7.2198. Min Act: -0.1700
Data Index: 5727636 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2198. Min Range: -7.2198
Max Act: 7.1886. Min Act: -0.1700
Data Index: 744517 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2198. Min Range: -7.2198
Max Act: 7.0636. Min Act: -0.1700
Data Index: 6382081 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2198. Min Range: -7.2198
Max Act: 7.0636. Min Act: -0.1700
Data Index: 7379335 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2198. Min Range: -7.2198
Max Act: 7.0636. Min Act: -0.1700
Data Index: 6676991 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2198. Min Range: -7.2198
Max Act: 7.0323. Min Act: -0.1700
Data Index: 813870 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2198. Min Range: -7.2198
Max Act: 7.0323. Min Act: -0.1700
Data Index: 3306949 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2198. Min Range: -7.2198
Max Act: 7.0011. Min Act: -0.1700
Data Index: 771079 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2198. Min Range: -7.2198
Max Act: 7.0011. Min Act: -0.1700
Data Index: 4104478 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.9698. Min Act: -0.1700
Data Index: 6744213 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.9073. Min Act: -0.1700
Data Index: 229943 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.9386. Min Act: -0.1700
Data Index: 388466 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.9073. Min Act: -0.1700
Data Index: 7218467 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.9073. Min Act: -0.1700
Data Index: 3727710 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.9073. Min Act: -0.1700
Data Index: 3553898 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.9073. Min Act: -0.1700
Data Index: 6719878 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.9073. Min Act: -0.1700
Data Index: 1481960 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.8761. Min Act: -0.1700
Data Index: 5769618 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.8448. Min Act: -0.1700
Data Index: 2448868 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2198. Min Range: -7.2198
Max Act: 6.8761. Min Act: -0.1700
Data Index: 1195736 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19