Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2575. Min Range: -6.2575
Max Act: 6.2575. Min Act: -0.1700
Data Index: 1680998 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2575. Min Range: -6.2575
Max Act: 6.1012. Min Act: -0.1700
Data Index: 6060661 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2575. Min Range: -6.2575
Max Act: 6.0700. Min Act: -0.1700
Data Index: 2263863 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.9137. Min Act: -0.1700
Data Index: 5334197 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.8512. Min Act: -0.1700
Data Index: 6714806 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.8512. Min Act: -0.1700
Data Index: 7040961 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.7887. Min Act: -0.1700
Data Index: 7385993 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.8200. Min Act: -0.1700
Data Index: 5802309 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.8200. Min Act: -0.1700
Data Index: 73289 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.7887. Min Act: -0.1700
Data Index: 6215408 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.7887. Min Act: -0.1700
Data Index: 5452930 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.7887. Min Act: -0.1700
Data Index: 2179223 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.7887. Min Act: -0.1700
Data Index: 5331270 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.6950. Min Act: -0.1700
Data Index: 791 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.6950. Min Act: -0.1700
Data Index: 1407851 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.7262. Min Act: -0.1700
Data Index: 7224707 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.6637. Min Act: -0.1700
Data Index: 2896756 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.6637. Min Act: -0.1700
Data Index: 1008044 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.6637. Min Act: -0.1700
Data Index: 4171897 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2575. Min Range: -6.2575
Max Act: 5.6637. Min Act: -0.1700
Data Index: 1321680 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19