Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4765 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.6363. Min Act: -0.1700
Data Index: 8422230 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.4800. Min Act: -0.1700
Data Index: 3214335 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.4488. Min Act: -0.1700
Data Index: 4009483 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.4175. Min Act: -0.1700
Data Index: 4341926 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.3550. Min Act: -0.1700
Data Index: 1386434 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.3550. Min Act: -0.1700
Data Index: 1080817 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.3550. Min Act: -0.1700
Data Index: 5282766 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.3238. Min Act: -0.1700
Data Index: 4651372 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.3238. Min Act: -0.1700
Data Index: 2196358 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.3238. Min Act: -0.1700
Data Index: 2946736 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.2925. Min Act: -0.1700
Data Index: 5219961 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.2613. Min Act: -0.1700
Data Index: 4143422 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.2613. Min Act: -0.1700
Data Index: 3368310 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.2613. Min Act: -0.1700
Data Index: 5910518 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.2300. Min Act: -0.1700
Data Index: 3543223 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.1675. Min Act: -0.1700
Data Index: 865688 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.2300. Min Act: -0.1700
Data Index: 2258722 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.1988. Min Act: -0.1700
Data Index: 1475892 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.1675. Min Act: -0.1700
Data Index: 2196357 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6363. Min Range: -5.6363
Max Act: 5.1675. Min Act: -0.1700
Data Index: 1584365 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19