Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.9889. Min Act: -0.1700
Data Index: 6257953 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.8327. Min Act: -0.1700
Data Index: 6908510 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.6452. Min Act: -0.1700
Data Index: 2707188 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.6452. Min Act: -0.1700
Data Index: 7045684 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.6452. Min Act: -0.1700
Data Index: 6877296 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.6139. Min Act: -0.1700
Data Index: 8476826 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.6139. Min Act: -0.1700
Data Index: 78671 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.5827. Min Act: -0.1700
Data Index: 6593374 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.5514. Min Act: -0.1700
Data Index: 2019121 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.5514. Min Act: -0.1700
Data Index: 3621497 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.5202. Min Act: -0.1700
Data Index: 2878750 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.5514. Min Act: -0.1700
Data Index: 6141828 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.4889. Min Act: -0.1700
Data Index: 7927935 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.4889. Min Act: -0.1700
Data Index: 8398989 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.4577. Min Act: -0.1700
Data Index: 5977292 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.4577. Min Act: -0.1700
Data Index: 3436618 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.3952. Min Act: -0.1700
Data Index: 3754584 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.4264. Min Act: -0.1700
Data Index: 4492053 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.3639. Min Act: -0.1700
Data Index: 6497956 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9889. Min Range: -6.9889
Max Act: 6.3952. Min Act: -0.1700
Data Index: 7152520 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19