Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.3825. Min Act: -0.1700
Data Index: 2632705 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1325. Min Act: -0.1700
Data Index: 7333407 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1325. Min Act: -0.1700
Data Index: 6887520 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1325. Min Act: -0.1700
Data Index: 902971 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1012. Min Act: -0.1700
Data Index: 7717839 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1325. Min Act: -0.1700
Data Index: 1930429 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1325. Min Act: -0.1700
Data Index: 5546340 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.0699. Min Act: -0.1700
Data Index: 5546339 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1012. Min Act: -0.1700
Data Index: 1664480 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1012. Min Act: -0.1700
Data Index: 7697169 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1012. Min Act: -0.1698
Data Index: 2109716 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1012. Min Act: -0.1700
Data Index: 6371646 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1012. Min Act: -0.1700
Data Index: 4400625 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.1012. Min Act: -0.1700
Data Index: 8127845 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.0699. Min Act: -0.1700
Data Index: 5357338 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.0699. Min Act: -0.1700
Data Index: 5546337 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.0699. Min Act: -0.1700
Data Index: 2360911 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.0699. Min Act: -0.1700
Data Index: 7874099 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.0699. Min Act: -0.1700
Data Index: 6575873 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3825. Min Range: -4.3825
Max Act: 4.0699. Min Act: -0.1700
Data Index: 3961170 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19