Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3262 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.6463. Min Act: -0.1700
Data Index: 3897960 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.6150. Min Act: -0.1700
Data Index: 8272119 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.5213. Min Act: -0.1700
Data Index: 8544378 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.5213. Min Act: -0.1700
Data Index: 6417051 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.4588. Min Act: -0.1700
Data Index: 6326082 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.3963. Min Act: -0.1700
Data Index: 5901274 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.3650. Min Act: -0.1700
Data Index: 6304135 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.3963. Min Act: -0.1700
Data Index: 4972337 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.3650. Min Act: -0.1700
Data Index: 4385107 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.3338. Min Act: -0.1700
Data Index: 7682359 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.2713. Min Act: -0.1700
Data Index: 8226253 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.2400. Min Act: -0.1700
Data Index: 4767732 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.2400. Min Act: -0.1700
Data Index: 5026934 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.2400. Min Act: -0.1700
Data Index: 5716369 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.2088. Min Act: -0.1700
Data Index: 6994926 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.2088. Min Act: -0.1700
Data Index: 3140920 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.2088. Min Act: -0.1700
Data Index: 8423233 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.1775. Min Act: -0.1700
Data Index: 326700 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.1775. Min Act: -0.1700
Data Index: 2843768 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6463. Min Range: -6.6463
Max Act: 6.1150. Min Act: -0.1700
Data Index: 5695198 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19