Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2580. Min Range: -8.2580
Max Act: 8.2580. Min Act: -0.1700
Data Index: 1354722 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.8830. Min Act: -0.1700
Data Index: 3750648 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.8205. Min Act: -0.1700
Data Index: 1370517 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.6955. Min Act: -0.1700
Data Index: 4925047 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.6955. Min Act: -0.1700
Data Index: 8162911 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.6330. Min Act: -0.1700
Data Index: 4777718 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.5393. Min Act: -0.1700
Data Index: 8393277 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.4455. Min Act: -0.1700
Data Index: 83350 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.4143. Min Act: -0.1700
Data Index: 8047712 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.4143. Min Act: -0.1700
Data Index: 1399611 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.3830. Min Act: -0.1700
Data Index: 5005009 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.3830. Min Act: -0.1700
Data Index: 3490276 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.3518. Min Act: -0.1700
Data Index: 711160 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.3205. Min Act: -0.1700
Data Index: 8414062 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.2893. Min Act: -0.1700
Data Index: 8402484 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.3205. Min Act: -0.1700
Data Index: 3697914 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.2580. Min Act: -0.1700
Data Index: 3250363 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.2893. Min Act: -0.1700
Data Index: 7582967 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.2580. Min Act: -0.1700
Data Index: 2586131 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2580. Min Range: -8.2580
Max Act: 7.2580. Min Act: -0.1700
Data Index: 2844063 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19