Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2501 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.7997. Min Act: -0.1700
Data Index: 7000600 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.7372. Min Act: -0.1700
Data Index: 2925297 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.5810. Min Act: -0.1700
Data Index: 5661346 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.5185. Min Act: -0.1700
Data Index: 399332 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.5497. Min Act: -0.1700
Data Index: 2541975 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.5185. Min Act: -0.1700
Data Index: 4724778 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.5185. Min Act: -0.1700
Data Index: 7553841 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.5185. Min Act: -0.1700
Data Index: 6238134 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.4872. Min Act: -0.1700
Data Index: 1275559 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.5185. Min Act: -0.1700
Data Index: 317813 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.4560. Min Act: -0.1700
Data Index: 2311827 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.4560. Min Act: -0.1700
Data Index: 4083975 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.4247. Min Act: -0.1700
Data Index: 5774823 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.3935. Min Act: -0.1700
Data Index: 7753697 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.3622. Min Act: -0.1700
Data Index: 3410846 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.3935. Min Act: -0.1700
Data Index: 3350229 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.3935. Min Act: -0.1700
Data Index: 5140730 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.3622. Min Act: -0.1700
Data Index: 873846 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.3310. Min Act: -0.1700
Data Index: 7124581 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7997. Min Range: -5.7997
Max Act: 5.2997. Min Act: -0.1700
Data Index: 2286364 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19