Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4450. Min Range: -5.4450
Max Act: 5.4450. Min Act: -0.1700
Data Index: 4294256 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4450. Min Range: -5.4450
Max Act: 5.3825. Min Act: -0.1700
Data Index: 5101342 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4450. Min Range: -5.4450
Max Act: 5.0387. Min Act: -0.1700
Data Index: 908558 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4450. Min Range: -5.4450
Max Act: 5.0075. Min Act: -0.1700
Data Index: 2897077 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.9762. Min Act: -0.1700
Data Index: 7204315 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.9137. Min Act: -0.1700
Data Index: 7493104 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.8825. Min Act: -0.1700
Data Index: 2982844 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.8825. Min Act: -0.1700
Data Index: 6216875 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.8825. Min Act: -0.1700
Data Index: 1948337 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.8200. Min Act: -0.1700
Data Index: 7013688 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.8200. Min Act: -0.1700
Data Index: 2738419 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.7887. Min Act: -0.1700
Data Index: 399751 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.7887. Min Act: -0.1700
Data Index: 5765212 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.7887. Min Act: -0.1700
Data Index: 5109309 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.7575. Min Act: -0.1700
Data Index: 798807 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.7575. Min Act: -0.1700
Data Index: 4564586 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.7575. Min Act: -0.1700
Data Index: 1316173 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.7575. Min Act: -0.1700
Data Index: 3405112 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.7262. Min Act: -0.1700
Data Index: 5972095 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4450. Min Range: -5.4450
Max Act: 4.7262. Min Act: -0.1700
Data Index: 1576864 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19