Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2461 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.8155. Min Act: -0.1700
Data Index: 7133502 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.7217. Min Act: -0.1700
Data Index: 5463916 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.6278. Min Act: -0.1700
Data Index: 946300 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.5965. Min Act: -0.1700
Data Index: 2055631 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.5652. Min Act: -0.1700
Data Index: 8426752 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.5496. Min Act: -0.1700
Data Index: 3451934 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.5339. Min Act: -0.1700
Data Index: 3225940 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.5339. Min Act: -0.1700
Data Index: 419234 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4869. Min Act: -0.1700
Data Index: 1235557 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4869. Min Act: -0.1700
Data Index: 939736 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.5026. Min Act: -0.1700
Data Index: 1651207 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4869. Min Act: -0.1700
Data Index: 3281835 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4713. Min Act: -0.1700
Data Index: 5915795 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4556. Min Act: -0.1700
Data Index: 6014335 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4556. Min Act: -0.1700
Data Index: 1858934 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4399. Min Act: -0.1700
Data Index: 5256618 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4243. Min Act: -0.1700
Data Index: 3574074 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4086. Min Act: -0.1700
Data Index: 926635 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.4086. Min Act: -0.1700
Data Index: 7711001 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8155. Min Range: -3.8155
Max Act: 3.3929. Min Act: -0.1700
Data Index: 3331112 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19