Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1581 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0245. Min Range: -5.0245
Max Act: 5.0245. Min Act: -0.1700
Data Index: 2124091 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0245. Min Range: -5.0245
Max Act: 5.0245. Min Act: -0.1700
Data Index: 6486191 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0245. Min Range: -5.0245
Max Act: 5.0245. Min Act: -0.1700
Data Index: 1479057 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.9308. Min Act: -0.1700
Data Index: 4832119 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.9308. Min Act: -0.1700
Data Index: 86441 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.9308. Min Act: -0.1700
Data Index: 4832135 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.9308. Min Act: -0.1700
Data Index: 4832134 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.8995. Min Act: -0.1700
Data Index: 4832118 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.8683. Min Act: -0.1700
Data Index: 8832109 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.8683. Min Act: -0.1700
Data Index: 3561940 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.8683. Min Act: -0.1700
Data Index: 2549481 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.8683. Min Act: -0.1700
Data Index: 2549482 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.7745. Min Act: -0.1700
Data Index: 5774267 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.7745. Min Act: -0.1700
Data Index: 2137883 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.7433. Min Act: -0.1700
Data Index: 1781968 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.7433. Min Act: -0.1700
Data Index: 5650536 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.7120. Min Act: -0.1700
Data Index: 3296980 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.7120. Min Act: -0.1700
Data Index: 3653814 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.7120. Min Act: -0.1700
Data Index: 1379465 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0245. Min Range: -5.0245
Max Act: 4.7120. Min Act: -0.1700
Data Index: 6819407 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19