Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6333 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1573. Min Range: -6.1573
Max Act: 6.1573. Min Act: -0.1700
Data Index: 4951779 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1573. Min Range: -6.1573
Max Act: 6.0635. Min Act: -0.1700
Data Index: 4432896 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1573. Min Range: -6.1573
Max Act: 6.0010. Min Act: -0.1700
Data Index: 8655017 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.9073. Min Act: -0.1700
Data Index: 4464923 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.9073. Min Act: -0.1700
Data Index: 7374718 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.8448. Min Act: -0.1700
Data Index: 270244 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.8760. Min Act: -0.1700
Data Index: 6241022 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.8448. Min Act: -0.1700
Data Index: 7478745 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.8135. Min Act: -0.1700
Data Index: 1648205 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.8135. Min Act: -0.1700
Data Index: 5418363 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7823. Min Act: -0.1700
Data Index: 5801979 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7510. Min Act: -0.1700
Data Index: 3596619 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7510. Min Act: -0.1700
Data Index: 6027195 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7510. Min Act: -0.1700
Data Index: 4885221 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7510. Min Act: -0.1700
Data Index: 8388405 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7510. Min Act: -0.1700
Data Index: 5997033 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7198. Min Act: -0.1700
Data Index: 3652557 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7198. Min Act: -0.1700
Data Index: 1812489 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7198. Min Act: -0.1700
Data Index: 2266177 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1573. Min Range: -6.1573
Max Act: 5.7198. Min Act: -0.1700
Data Index: 7409681 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19