Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 911 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.5879. Min Act: -0.1700
Data Index: 1298576 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.4629. Min Act: -0.1700
Data Index: 2192688 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.4629. Min Act: -0.1700
Data Index: 7102480 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.4004. Min Act: -0.1700
Data Index: 4943634 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3691. Min Act: -0.1700
Data Index: 3527283 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3691. Min Act: -0.1700
Data Index: 1622391 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3691. Min Act: -0.1700
Data Index: 2908694 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3691. Min Act: -0.1700
Data Index: 726850 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3066. Min Act: -0.1700
Data Index: 4585319 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3691. Min Act: -0.1700
Data Index: 8306237 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3379. Min Act: -0.1698
Data Index: 730153 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3066. Min Act: -0.1700
Data Index: 533293 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3066. Min Act: -0.1700
Data Index: 3979370 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3066. Min Act: -0.1700
Data Index: 3328717 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3066. Min Act: -0.1700
Data Index: 1098624 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3066. Min Act: -0.1700
Data Index: 4888222 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.2754. Min Act: -0.1700
Data Index: 2444083 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.2754. Min Act: -0.1700
Data Index: 4276164 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.3066. Min Act: -0.1700
Data Index: 2767032 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5879. Min Range: -5.5879
Max Act: 5.2441. Min Act: -0.1700
Data Index: 1292103 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19