Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4540 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.6748. Min Act: -0.1700
Data Index: 3171281 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.5498. Min Act: -0.1700
Data Index: 5296732 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.5498. Min Act: -0.1700
Data Index: 1953805 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.3936. Min Act: -0.1700
Data Index: 2976530 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.4248. Min Act: -0.1700
Data Index: 8268109 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.4248. Min Act: -0.1700
Data Index: 7005904 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.3623. Min Act: -0.1700
Data Index: 6653974 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.2061. Min Act: -0.1700
Data Index: 623919 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.2061. Min Act: -0.1700
Data Index: 622297 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.1748. Min Act: -0.1700
Data Index: 2206660 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.1748. Min Act: -0.1700
Data Index: 8271237 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.1123. Min Act: -0.1700
Data Index: 7145389 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.1123. Min Act: -0.1700
Data Index: 8601491 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.0498. Min Act: -0.1700
Data Index: 7342789 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.0186. Min Act: -0.1700
Data Index: 3464823 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6748. Min Range: -7.6748
Max Act: 7.0186. Min Act: -0.1700
Data Index: 1976739 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6748. Min Range: -7.6748
Max Act: 6.9873. Min Act: -0.1700
Data Index: 6953487 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6748. Min Range: -7.6748
Max Act: 6.9248. Min Act: -0.1700
Data Index: 6030732 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6748. Min Range: -7.6748
Max Act: 6.9248. Min Act: -0.1700
Data Index: 8796973 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6748. Min Range: -7.6748
Max Act: 6.8936. Min Act: -0.1700
Data Index: 7507203 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19