Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4852 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.7106. Min Act: -0.1700
Data Index: 4448216 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.6481. Min Act: -0.1700
Data Index: 8533871 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.6481. Min Act: -0.1700
Data Index: 7544955 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.6168. Min Act: -0.1700
Data Index: 2889736 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.4918. Min Act: -0.1700
Data Index: 686378 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.4293. Min Act: -0.1700
Data Index: 3122865 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.4293. Min Act: -0.1700
Data Index: 8525471 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.3981. Min Act: -0.1700
Data Index: 4165064 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.3668. Min Act: -0.1700
Data Index: 1256610 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.3668. Min Act: -0.1700
Data Index: 2501415 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.3668. Min Act: -0.1700
Data Index: 270540 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.3668. Min Act: -0.1700
Data Index: 2547344 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.3356. Min Act: -0.1700
Data Index: 5535219 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.3043. Min Act: -0.1700
Data Index: 6040594 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.3043. Min Act: -0.1700
Data Index: 8737767 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.2731. Min Act: -0.1700
Data Index: 7389689 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.2418. Min Act: -0.1700
Data Index: 4379564 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.2418. Min Act: -0.1700
Data Index: 8230446 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.2106. Min Act: -0.1700
Data Index: 5031646 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7106. Min Range: -6.7106
Max Act: 6.2418. Min Act: -0.1700
Data Index: 5443234 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19