Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4979 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.4845. Min Act: -0.1700
Data Index: 7562581 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.4220. Min Act: -0.1700
Data Index: 4458025 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.3595. Min Act: -0.1700
Data Index: 5341280 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.3595. Min Act: -0.1700
Data Index: 1146329 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.2970. Min Act: -0.1700
Data Index: 5111243 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.2658. Min Act: -0.1700
Data Index: 1312938 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1720. Min Act: -0.1700
Data Index: 6974685 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1720. Min Act: -0.1700
Data Index: 2472637 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1408. Min Act: -0.1700
Data Index: 3863107 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1408. Min Act: -0.1700
Data Index: 4451476 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1408. Min Act: -0.1700
Data Index: 7479314 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1408. Min Act: -0.1700
Data Index: 4138861 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1095. Min Act: -0.1700
Data Index: 2183765 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1095. Min Act: -0.1700
Data Index: 43799 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1095. Min Act: -0.1700
Data Index: 1717429 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1095. Min Act: -0.1700
Data Index: 4843518 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1095. Min Act: -0.1700
Data Index: 4804253 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1095. Min Act: -0.1700
Data Index: 3913556 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.0783. Min Act: -0.1700
Data Index: 1776292 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4845. Min Range: -5.4845
Max Act: 5.1095. Min Act: -0.1700
Data Index: 359790 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19