Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3720. Min Range: -6.3720
Max Act: 6.3720. Min Act: -0.1700
Data Index: 5580156 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3720. Min Range: -6.3720
Max Act: 6.3720. Min Act: -0.1700
Data Index: 7188643 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3720. Min Range: -6.3720
Max Act: 6.2158. Min Act: -0.1700
Data Index: 6579529 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3720. Min Range: -6.3720
Max Act: 6.1845. Min Act: -0.1700
Data Index: 7299823 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.9970. Min Act: -0.1700
Data Index: 234499 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3720. Min Range: -6.3720
Max Act: 6.0283. Min Act: -0.1700
Data Index: 2686850 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.9970. Min Act: -0.1700
Data Index: 6930148 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.9658. Min Act: -0.1700
Data Index: 4674681 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.9970. Min Act: -0.1700
Data Index: 6247828 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.9658. Min Act: -0.1700
Data Index: 4509800 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.9345. Min Act: -0.1700
Data Index: 3652022 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.9033. Min Act: -0.1700
Data Index: 8388560 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.9033. Min Act: -0.1700
Data Index: 7722536 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.9033. Min Act: -0.1700
Data Index: 2183463 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.8408. Min Act: -0.1700
Data Index: 7745200 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.8408. Min Act: -0.1700
Data Index: 1008513 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.8408. Min Act: -0.1700
Data Index: 5438854 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.8408. Min Act: -0.1700
Data Index: 7736142 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.8095. Min Act: -0.1700
Data Index: 2443096 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3720. Min Range: -6.3720
Max Act: 5.8095. Min Act: -0.1700
Data Index: 714292 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19