Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5922 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.5376. Min Act: -0.1700
Data Index: 2143232 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.5376. Min Act: -0.1700
Data Index: 8821984 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.5062. Min Act: -0.1700
Data Index: 55533 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.4436. Min Act: -0.1700
Data Index: 3612459 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3495. Min Act: -0.1700
Data Index: 5427623 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3652. Min Act: -0.1700
Data Index: 1156465 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3652. Min Act: -0.1700
Data Index: 4610523 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3338. Min Act: -0.1700
Data Index: 5153022 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3024. Min Act: -0.1700
Data Index: 6303522 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3024. Min Act: -0.1700
Data Index: 5625676 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3024. Min Act: -0.1700
Data Index: 1211022 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2867. Min Act: -0.1700
Data Index: 4032976 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2867. Min Act: -0.1700
Data Index: 6348832 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2867. Min Act: -0.1700
Data Index: 269976 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2867. Min Act: -0.1700
Data Index: 6850259 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2867. Min Act: -0.1700
Data Index: 7237893 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2867. Min Act: -0.1700
Data Index: 43565 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2867. Min Act: -0.1700
Data Index: 7059582 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2553. Min Act: -0.1700
Data Index: 6816175 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2710. Min Act: -0.1700
Data Index: 1174181 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19