Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1664 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0238. Min Range: -6.0238
Max Act: 6.0238. Min Act: -0.1700
Data Index: 4028730 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.9613. Min Act: -0.1700
Data Index: 7373195 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.8988. Min Act: -0.1700
Data Index: 4280448 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.7425. Min Act: -0.1700
Data Index: 997643 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.6800. Min Act: -0.1700
Data Index: 121869 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.6175. Min Act: -0.1700
Data Index: 5064008 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.6175. Min Act: -0.1700
Data Index: 5582770 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5550. Min Act: -0.1700
Data Index: 8330529 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5238. Min Act: -0.1700
Data Index: 4042395 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5550. Min Act: -0.1700
Data Index: 8182317 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.4925. Min Act: -0.1700
Data Index: 2872797 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.4925. Min Act: -0.1700
Data Index: 1439140 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.4925. Min Act: -0.1700
Data Index: 5235426 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.4925. Min Act: -0.1700
Data Index: 742032 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.4613. Min Act: -0.1700
Data Index: 4557126 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.4613. Min Act: -0.1700
Data Index: 3818304 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.4300. Min Act: -0.1700
Data Index: 5712945 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.3988. Min Act: -0.1700
Data Index: 8099534 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.4613. Min Act: -0.1700
Data Index: 2841771 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.4300. Min Act: -0.1700
Data Index: 3057862 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19