Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6335 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.6836. Min Act: -0.1700
Data Index: 2406792 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.6211. Min Act: -0.1700
Data Index: 2561022 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.5586. Min Act: -0.1700
Data Index: 3223946 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.5586. Min Act: -0.1700
Data Index: 5895942 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.5274. Min Act: -0.1700
Data Index: 8342706 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.5274. Min Act: -0.1700
Data Index: 5779260 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.4649. Min Act: -0.1700
Data Index: 6898977 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.4336. Min Act: -0.1700
Data Index: 4056324 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.4336. Min Act: -0.1700
Data Index: 8800414 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.4649. Min Act: -0.1700
Data Index: 1322813 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.4336. Min Act: -0.1700
Data Index: 4895947 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.4336. Min Act: -0.1700
Data Index: 4014958 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.4649. Min Act: -0.1700
Data Index: 3415335 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.4024. Min Act: -0.1700
Data Index: 1397630 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.4336. Min Act: -0.1700
Data Index: 4131006 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.3711. Min Act: -0.1700
Data Index: 1851654 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.3711. Min Act: -0.1700
Data Index: 6594272 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.3399. Min Act: -0.1700
Data Index: 4652771 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.3086. Min Act: -0.1700
Data Index: 1473060 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6836. Min Range: -4.6836
Max Act: 4.3399. Min Act: -0.1700
Data Index: 4919518 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19