Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2728 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.8182. Min Act: -0.1700
Data Index: 4271712 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.7869. Min Act: -0.1700
Data Index: 5594686 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.7244. Min Act: -0.1700
Data Index: 2840489 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.4744. Min Act: -0.1700
Data Index: 5173698 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.4432. Min Act: -0.1700
Data Index: 3196494 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.4119. Min Act: -0.1700
Data Index: 3824420 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.4119. Min Act: -0.1700
Data Index: 5516041 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.4119. Min Act: -0.1700
Data Index: 2380614 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.4119. Min Act: -0.1700
Data Index: 802942 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.3494. Min Act: -0.1700
Data Index: 537140 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.3182. Min Act: -0.1700
Data Index: 2271579 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.3182. Min Act: -0.1700
Data Index: 2036696 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.2869. Min Act: -0.1700
Data Index: 1898727 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.3182. Min Act: -0.1700
Data Index: 1821515 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.2869. Min Act: -0.1700
Data Index: 3616199 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.2557. Min Act: -0.1700
Data Index: 8735042 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.2557. Min Act: -0.1700
Data Index: 8451542 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.2557. Min Act: -0.1700
Data Index: 2483430 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.2244. Min Act: -0.1700
Data Index: 2723783 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8182. Min Range: -5.8182
Max Act: 5.2244. Min Act: -0.1700
Data Index: 1801180 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19