Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5019. Min Range: -8.5019
Max Act: 8.5019. Min Act: -0.1700
Data Index: 8456306 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5019. Min Range: -8.5019
Max Act: 8.1581. Min Act: -0.1700
Data Index: 6152094 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5019. Min Range: -8.5019
Max Act: 8.0956. Min Act: -0.1700
Data Index: 8049951 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.8456. Min Act: -0.1700
Data Index: 140496 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.7206. Min Act: -0.1700
Data Index: 5875207 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.6581. Min Act: -0.1700
Data Index: 3886162 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.6581. Min Act: -0.1700
Data Index: 8211894 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.5644. Min Act: -0.1700
Data Index: 6591910 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.5644. Min Act: -0.1700
Data Index: 7053345 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.5331. Min Act: -0.1700
Data Index: 3159558 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.5331. Min Act: -0.1700
Data Index: 7518466 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.5331. Min Act: -0.1700
Data Index: 6027442 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.5019. Min Act: -0.1700
Data Index: 3640662 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.5019. Min Act: -0.1700
Data Index: 6431839 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.5019. Min Act: -0.1700
Data Index: 467633 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.5019. Min Act: -0.1700
Data Index: 3375329 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.4394. Min Act: -0.1700
Data Index: 1340135 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.4706. Min Act: -0.1700
Data Index: 6623080 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.4706. Min Act: -0.1700
Data Index: 3350589 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5019. Min Range: -8.5019
Max Act: 7.4394. Min Act: -0.1700
Data Index: 3600176 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19