Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 893 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.2989. Min Act: -0.1700
Data Index: 4886589 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.1426. Min Act: -0.1700
Data Index: 4637932 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.1426. Min Act: -0.1700
Data Index: 7380196 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0801. Min Act: -0.1700
Data Index: 1745411 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0489. Min Act: -0.1700
Data Index: 5270135 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0489. Min Act: -0.1700
Data Index: 3482573 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0489. Min Act: -0.1700
Data Index: 7172568 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0489. Min Act: -0.1700
Data Index: 8366144 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0489. Min Act: -0.1700
Data Index: 5658990 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0489. Min Act: -0.1700
Data Index: 3614997 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0176. Min Act: -0.1700
Data Index: 4075206 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0176. Min Act: -0.1700
Data Index: 1945865 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2989. Min Range: -5.2989
Max Act: 4.9864. Min Act: -0.1700
Data Index: 3318632 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2989. Min Range: -5.2989
Max Act: 5.0176. Min Act: -0.1700
Data Index: 4550492 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2989. Min Range: -5.2989
Max Act: 4.9864. Min Act: -0.1700
Data Index: 7717978 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2989. Min Range: -5.2989
Max Act: 4.9551. Min Act: -0.1700
Data Index: 228210 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2989. Min Range: -5.2989
Max Act: 4.9239. Min Act: -0.1700
Data Index: 3022206 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2989. Min Range: -5.2989
Max Act: 4.9551. Min Act: -0.1700
Data Index: 5062704 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2989. Min Range: -5.2989
Max Act: 4.9239. Min Act: -0.1700
Data Index: 2899563 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2989. Min Range: -5.2989
Max Act: 4.9239. Min Act: -0.1700
Data Index: 2928137 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19