Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.9770. Min Act: -0.1700
Data Index: 8721485 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.8520. Min Act: -0.1700
Data Index: 8063263 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.8520. Min Act: -0.1700
Data Index: 3161957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.8520. Min Act: -0.1700
Data Index: 2247502 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.7895. Min Act: -0.1700
Data Index: 802351 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.7583. Min Act: -0.1700
Data Index: 4011452 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.7270. Min Act: -0.1700
Data Index: 8219525 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6958. Min Act: -0.1700
Data Index: 3880773 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6958. Min Act: -0.1700
Data Index: 7716892 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6958. Min Act: -0.1700
Data Index: 4087881 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6958. Min Act: -0.1700
Data Index: 6294476 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6645. Min Act: -0.1700
Data Index: 7090081 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6645. Min Act: -0.1700
Data Index: 3322600 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6645. Min Act: -0.1700
Data Index: 2520776 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6645. Min Act: -0.1700
Data Index: 460143 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6645. Min Act: -0.1700
Data Index: 5884730 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6645. Min Act: -0.1700
Data Index: 4970199 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6645. Min Act: -0.1700
Data Index: 3216613 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6645. Min Act: -0.1700
Data Index: 176096 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9770. Min Range: -5.9770
Max Act: 5.6333. Min Act: -0.1700
Data Index: 1480401 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19