Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 167 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.7412. Min Act: -0.1700
Data Index: 2349729 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.6787. Min Act: -0.1700
Data Index: 1736591 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.6787. Min Act: -0.1700
Data Index: 6568279 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.6475. Min Act: -0.1700
Data Index: 6962819 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.6475. Min Act: -0.1700
Data Index: 5288968 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.6162. Min Act: -0.1700
Data Index: 4069033 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.5225. Min Act: -0.1700
Data Index: 3700427 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.5225. Min Act: -0.1700
Data Index: 6894564 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.4912. Min Act: -0.1700
Data Index: 8496716 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.4912. Min Act: -0.1700
Data Index: 6021089 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.4912. Min Act: -0.1700
Data Index: 2030857 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.4287. Min Act: -0.1700
Data Index: 7102618 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.4287. Min Act: -0.1700
Data Index: 6184108 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.3975. Min Act: -0.1700
Data Index: 6962818 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.4287. Min Act: -0.1700
Data Index: 3518140 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.4287. Min Act: -0.1700
Data Index: 2767526 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.3975. Min Act: -0.1700
Data Index: 3009138 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.3662. Min Act: -0.1700
Data Index: 4596660 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.3662. Min Act: -0.1700
Data Index: 1130836 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7412. Min Range: -4.7412
Max Act: 4.3662. Min Act: -0.1700
Data Index: 6876362 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19