Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.1630. Min Act: -0.1700
Data Index: 6129423 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1630. Min Range: -5.1630
Max Act: 5.0380. Min Act: -0.1700
Data Index: 1948031 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.9755. Min Act: -0.1700
Data Index: 3669539 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.9443. Min Act: -0.1700
Data Index: 2557194 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.8193. Min Act: -0.1700
Data Index: 4991869 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.8193. Min Act: -0.1700
Data Index: 8617885 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.7880. Min Act: -0.1700
Data Index: 4192782 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.8505. Min Act: -0.1700
Data Index: 5486233 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.7255. Min Act: -0.1700
Data Index: 2187756 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.7568. Min Act: -0.1700
Data Index: 8265330 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.7568. Min Act: -0.1700
Data Index: 1712554 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.7255. Min Act: -0.1700
Data Index: 4215586 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.7255. Min Act: -0.1700
Data Index: 4656177 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.7255. Min Act: -0.1700
Data Index: 6957815 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.6943. Min Act: -0.1700
Data Index: 4878241 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.6630. Min Act: -0.1700
Data Index: 8175444 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.6630. Min Act: -0.1700
Data Index: 7109952 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.6630. Min Act: -0.1700
Data Index: 3688562 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.6943. Min Act: -0.1700
Data Index: 680067 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1630. Min Range: -5.1630
Max Act: 4.6630. Min Act: -0.1700
Data Index: 8185437 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19