Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4003 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2127. Min Range: -10.2127
Max Act: 10.2127. Min Act: -0.1700
Data Index: 1476654 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2127. Min Range: -10.2127
Max Act: 10.0877. Min Act: -0.1700
Data Index: 3626658 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2127. Min Range: -10.2127
Max Act: 10.0252. Min Act: -0.1700
Data Index: 1840416 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.9627. Min Act: -0.1700
Data Index: 1188262 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.9627. Min Act: -0.1700
Data Index: 2059432 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.8377. Min Act: -0.1700
Data Index: 3596670 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.8377. Min Act: -0.1700
Data Index: 1945961 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.7752. Min Act: -0.1700
Data Index: 1381805 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.7752. Min Act: -0.1700
Data Index: 4564860 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.7752. Min Act: -0.1700
Data Index: 7554800 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.6502. Min Act: -0.1700
Data Index: 367083 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.5877. Min Act: -0.1700
Data Index: 3409678 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.5252. Min Act: -0.1700
Data Index: 5684375 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.5252. Min Act: -0.1700
Data Index: 7952302 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.4627. Min Act: -0.1700
Data Index: 5392817 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.4002. Min Act: -0.1700
Data Index: 8826492 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.2752. Min Act: -0.1700
Data Index: 529721 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.3377. Min Act: -0.1700
Data Index: 2799501 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.2752. Min Act: -0.1700
Data Index: 2591193 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2127. Min Range: -10.2127
Max Act: 9.2752. Min Act: -0.1700
Data Index: 8525227 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19