Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.4735. Min Act: -0.1700
Data Index: 58563 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.4422. Min Act: -0.1700
Data Index: 8424997 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.4735. Min Act: -0.1700
Data Index: 3852736 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.3172. Min Act: -0.1700
Data Index: 3101570 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.3172. Min Act: -0.1700
Data Index: 7260833 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.2860. Min Act: -0.1700
Data Index: 1400227 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.2860. Min Act: -0.1700
Data Index: 6951308 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.2860. Min Act: -0.1700
Data Index: 5409499 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.2860. Min Act: -0.1700
Data Index: 4983461 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.2235. Min Act: -0.1700
Data Index: 8306269 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.2547. Min Act: -0.1700
Data Index: 2887461 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.1610. Min Act: -0.1700
Data Index: 4736934 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.1610. Min Act: -0.1700
Data Index: 4008702 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.1610. Min Act: -0.1700
Data Index: 4743999 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.1297. Min Act: -0.1700
Data Index: 8734933 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.1297. Min Act: -0.1700
Data Index: 1385333 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.1610. Min Act: -0.1700
Data Index: 101801 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.1297. Min Act: -0.1700
Data Index: 5409174 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.1297. Min Act: -0.1700
Data Index: 4083572 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4735. Min Range: -5.4735
Max Act: 5.1297. Min Act: -0.1700
Data Index: 597700 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19