Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3854 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.6778. Min Act: -0.1700
Data Index: 8140469 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.6153. Min Act: -0.1700
Data Index: 2637312 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.4278. Min Act: -0.1700
Data Index: 362457 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.2716. Min Act: -0.1700
Data Index: 2789506 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.2091. Min Act: -0.1700
Data Index: 462572 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.2091. Min Act: -0.1700
Data Index: 8083869 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.1466. Min Act: -0.1700
Data Index: 39243 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.1153. Min Act: -0.1700
Data Index: 5689137 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.1153. Min Act: -0.1700
Data Index: 867559 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.1153. Min Act: -0.1700
Data Index: 1202282 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.0528. Min Act: -0.1700
Data Index: 7993237 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.0528. Min Act: -0.1700
Data Index: 4938993 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6778. Min Range: -7.6778
Max Act: 7.0216. Min Act: -0.1700
Data Index: 3216632 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6778. Min Range: -7.6778
Max Act: 6.9903. Min Act: -0.1700
Data Index: 7433950 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6778. Min Range: -7.6778
Max Act: 6.9903. Min Act: -0.1700
Data Index: 1354472 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6778. Min Range: -7.6778
Max Act: 6.9903. Min Act: -0.1700
Data Index: 8282676 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6778. Min Range: -7.6778
Max Act: 6.9903. Min Act: -0.1700
Data Index: 5602034 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6778. Min Range: -7.6778
Max Act: 6.9903. Min Act: -0.1700
Data Index: 7910843 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6778. Min Range: -7.6778
Max Act: 6.9591. Min Act: -0.1700
Data Index: 3255110 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6778. Min Range: -7.6778
Max Act: 6.9903. Min Act: -0.1700
Data Index: 2114477 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19