Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.9709. Min Act: -0.1700
Data Index: 6351047 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.9084. Min Act: -0.1700
Data Index: 4903253 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8459. Min Act: -0.1700
Data Index: 5352699 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8772. Min Act: -0.1700
Data Index: 6192160 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8459. Min Act: -0.1700
Data Index: 8110513 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8146. Min Act: -0.1700
Data Index: 105364 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.8146. Min Act: -0.1700
Data Index: 7508897 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7990. Min Act: -0.1700
Data Index: 5737058 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7833. Min Act: -0.1700
Data Index: 311664 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7677. Min Act: -0.1700
Data Index: 1970295 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7208. Min Act: -0.1700
Data Index: 8826261 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7208. Min Act: -0.1700
Data Index: 138180 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7051. Min Act: -0.1700
Data Index: 5809628 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.7051. Min Act: -0.1700
Data Index: 4030192 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.6738. Min Act: -0.1700
Data Index: 6397405 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.6895. Min Act: -0.1700
Data Index: 7716215 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.6895. Min Act: -0.1700
Data Index: 2769055 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.6738. Min Act: -0.1700
Data Index: 6319856 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.6738. Min Act: -0.1700
Data Index: 3342729 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9709. Min Range: -3.9709
Max Act: 3.6738. Min Act: -0.1700
Data Index: 4248376 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19