Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4574 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3830. Min Range: -11.3830
Max Act: 11.3830. Min Act: -0.1700
Data Index: 297455 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3830. Min Range: -11.3830
Max Act: 11.3205. Min Act: -0.1700
Data Index: 4754848 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3830. Min Range: -11.3830
Max Act: 11.0080. Min Act: -0.1700
Data Index: 3086214 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3830. Min Range: -11.3830
Max Act: 11.0080. Min Act: -0.1700
Data Index: 3999374 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3830. Min Range: -11.3830
Max Act: 11.0080. Min Act: -0.1700
Data Index: 174967 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.9455. Min Act: -0.1700
Data Index: 889881 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.9455. Min Act: -0.1700
Data Index: 4199437 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.8205. Min Act: -0.1700
Data Index: 123610 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.8205. Min Act: -0.1700
Data Index: 5471615 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.7580. Min Act: -0.1700
Data Index: 4147610 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.7580. Min Act: -0.1700
Data Index: 6682491 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.7580. Min Act: -0.1700
Data Index: 1374687 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.7580. Min Act: -0.1700
Data Index: 7055129 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.6955. Min Act: -0.1700
Data Index: 3753613 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.6330. Min Act: -0.1700
Data Index: 43364 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.5705. Min Act: -0.1700
Data Index: 8630492 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.5705. Min Act: -0.1700
Data Index: 1546517 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.5705. Min Act: -0.1700
Data Index: 6829147 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.5705. Min Act: -0.1700
Data Index: 4195425 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3830. Min Range: -11.3830
Max Act: 10.5080. Min Act: -0.1700
Data Index: 2338311 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19