Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4332 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4385. Min Range: -6.4385
Max Act: 6.4385. Min Act: -0.1700
Data Index: 2223034 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4385. Min Range: -6.4385
Max Act: 6.3135. Min Act: -0.1700
Data Index: 6052144 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4385. Min Range: -6.4385
Max Act: 6.2198. Min Act: -0.1700
Data Index: 7226716 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4385. Min Range: -6.4385
Max Act: 6.1573. Min Act: -0.1700
Data Index: 331769 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4385. Min Range: -6.4385
Max Act: 6.1260. Min Act: -0.1700
Data Index: 8028633 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4385. Min Range: -6.4385
Max Act: 6.0010. Min Act: -0.1700
Data Index: 4754546 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.9698. Min Act: -0.1700
Data Index: 135255 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4385. Min Range: -6.4385
Max Act: 6.0010. Min Act: -0.1700
Data Index: 3005128 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.9698. Min Act: -0.1700
Data Index: 7625840 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.9385. Min Act: -0.1700
Data Index: 4515692 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.9073. Min Act: -0.1700
Data Index: 8218924 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.9073. Min Act: -0.1700
Data Index: 3590877 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.9385. Min Act: -0.1700
Data Index: 1276243 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.8760. Min Act: -0.1700
Data Index: 6157634 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.8760. Min Act: -0.1700
Data Index: 5980835 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.8760. Min Act: -0.1700
Data Index: 2483793 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.8760. Min Act: -0.1700
Data Index: 1530402 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.8135. Min Act: -0.1700
Data Index: 2810484 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.7823. Min Act: -0.1700
Data Index: 769638 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4385. Min Range: -6.4385
Max Act: 5.7823. Min Act: -0.1700
Data Index: 674785 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19