Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1210 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.2853. Min Act: -0.1700
Data Index: 144017 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.2228. Min Act: -0.1700
Data Index: 5668075 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.1916. Min Act: -0.1700
Data Index: 6195647 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.1291. Min Act: -0.1700
Data Index: 3010715 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.1291. Min Act: -0.1700
Data Index: 8016001 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.1291. Min Act: -0.1700
Data Index: 7469809 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0978. Min Act: -0.1700
Data Index: 1505346 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0978. Min Act: -0.1700
Data Index: 5422199 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0665. Min Act: -0.1700
Data Index: 8147546 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0665. Min Act: -0.1700
Data Index: 3475991 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0353. Min Act: -0.1700
Data Index: 3097088 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0353. Min Act: -0.1700
Data Index: 4798860 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0353. Min Act: -0.1700
Data Index: 978296 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0353. Min Act: -0.1700
Data Index: 1280346 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 714711 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0353. Min Act: -0.1700
Data Index: 1176116 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 3027758 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 6398676 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 1190084 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 5530475 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19