Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3240. Min Range: -8.3240
Max Act: 8.3240. Min Act: -0.1700
Data Index: 1933682 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3240. Min Range: -8.3240
Max Act: 8.0115. Min Act: -0.1700
Data Index: 2275670 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3240. Min Range: -8.3240
Max Act: 8.0115. Min Act: -0.1700
Data Index: 6771064 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.8865. Min Act: -0.1700
Data Index: 1157688 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.8865. Min Act: -0.1700
Data Index: 6939741 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.8865. Min Act: -0.1700
Data Index: 2379794 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.7615. Min Act: -0.1700
Data Index: 6826275 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.8240. Min Act: -0.1700
Data Index: 7842856 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.8240. Min Act: -0.1700
Data Index: 3794829 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.8240. Min Act: -0.1700
Data Index: 612986 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.6990. Min Act: -0.1700
Data Index: 3742059 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.7615. Min Act: -0.1700
Data Index: 6404257 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.7615. Min Act: -0.1700
Data Index: 2644695 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.7615. Min Act: -0.1700
Data Index: 6744837 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.7615. Min Act: -0.1700
Data Index: 924174 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.7615. Min Act: -0.1700
Data Index: 5573804 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.7615. Min Act: -0.1700
Data Index: 1177733 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.7615. Min Act: -0.1700
Data Index: 2140551 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.7615. Min Act: -0.1700
Data Index: 8269829 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3240. Min Range: -8.3240
Max Act: 7.6990. Min Act: -0.1700
Data Index: 8576513 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19