Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.7657. Min Act: -0.1700
Data Index: 3225359 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.5469. Min Act: -0.1700
Data Index: 3099747 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.4219. Min Act: -0.1700
Data Index: 3719859 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.2969. Min Act: -0.1700
Data Index: 3317679 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.2032. Min Act: -0.1700
Data Index: 8603917 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1719. Min Act: -0.1700
Data Index: 866995 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1407. Min Act: -0.1700
Data Index: 2693137 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1719. Min Act: -0.1700
Data Index: 4542291 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1407. Min Act: -0.1700
Data Index: 4304430 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1719. Min Act: -0.1700
Data Index: 5701030 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.2032. Min Act: -0.1700
Data Index: 1814704 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1094. Min Act: -0.1700
Data Index: 7238197 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1407. Min Act: -0.1700
Data Index: 7790240 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1407. Min Act: -0.1700
Data Index: 1249219 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1094. Min Act: -0.1700
Data Index: 3515843 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1407. Min Act: -0.1700
Data Index: 252574 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1094. Min Act: -0.1700
Data Index: 6392294 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1094. Min Act: -0.1700
Data Index: 5737718 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.1094. Min Act: -0.1700
Data Index: 3379689 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7657. Min Range: -7.7657
Max Act: 7.0782. Min Act: -0.1700
Data Index: 2023928 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19