Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2699. Min Range: -5.2699
Max Act: 5.2699. Min Act: -0.1700
Data Index: 3157113 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2699. Min Range: -5.2699
Max Act: 5.2386. Min Act: -0.1700
Data Index: 4967413 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2699. Min Range: -5.2699
Max Act: 5.1761. Min Act: -0.1700
Data Index: 1438612 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2699. Min Range: -5.2699
Max Act: 5.1136. Min Act: -0.1700
Data Index: 1067332 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2699. Min Range: -5.2699
Max Act: 5.1449. Min Act: -0.1700
Data Index: 5089714 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2699. Min Range: -5.2699
Max Act: 5.1136. Min Act: -0.1700
Data Index: 7095342 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2699. Min Range: -5.2699
Max Act: 5.0511. Min Act: -0.1700
Data Index: 833862 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.9261. Min Act: -0.1700
Data Index: 7342229 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.8949. Min Act: -0.1700
Data Index: 4709438 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.8636. Min Act: -0.1700
Data Index: 2731411 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.8636. Min Act: -0.1700
Data Index: 2736381 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.8324. Min Act: -0.1700
Data Index: 6747973 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.8011. Min Act: -0.1700
Data Index: 4921582 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.8011. Min Act: -0.1700
Data Index: 4125225 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.7699. Min Act: -0.1700
Data Index: 5760059 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.7699. Min Act: -0.1700
Data Index: 8423379 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.7699. Min Act: -0.1700
Data Index: 7003610 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.7699. Min Act: -0.1700
Data Index: 6147931 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.7699. Min Act: -0.1700
Data Index: 7257162 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2699. Min Range: -5.2699
Max Act: 4.7699. Min Act: -0.1700
Data Index: 6009406 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19