Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4870 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.4362. Min Act: -0.1700
Data Index: 3738484 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.4362. Min Act: -0.1700
Data Index: 6928123 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.3112. Min Act: -0.1700
Data Index: 799840 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.3112. Min Act: -0.1700
Data Index: 8385954 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.2487. Min Act: -0.1700
Data Index: 5288401 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.1862. Min Act: -0.1700
Data Index: 169185 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.1862. Min Act: -0.1700
Data Index: 5994540 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.1862. Min Act: -0.1700
Data Index: 5895838 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.1549. Min Act: -0.1700
Data Index: 4702174 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.1549. Min Act: -0.1700
Data Index: 3327061 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.1862. Min Act: -0.1700
Data Index: 4356189 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.1237. Min Act: -0.1700
Data Index: 1140626 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.0924. Min Act: -0.1700
Data Index: 2964831 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.0612. Min Act: -0.1700
Data Index: 105354 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.0299. Min Act: -0.1700
Data Index: 7973819 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.0612. Min Act: -0.1700
Data Index: 5578308 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4362. Min Range: -6.4362
Max Act: 5.9987. Min Act: -0.1700
Data Index: 4716052 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.0299. Min Act: -0.1700
Data Index: 1554848 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4362. Min Range: -6.4362
Max Act: 6.0612. Min Act: -0.1700
Data Index: 4405316 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4362. Min Range: -6.4362
Max Act: 5.9987. Min Act: -0.1700
Data Index: 5754468 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19