Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7369. Min Range: -8.7369
Max Act: 8.7369. Min Act: -0.1700
Data Index: 7814775 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.9869. Min Act: -0.1700
Data Index: 7769251 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.9869. Min Act: -0.1700
Data Index: 190438 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.5494. Min Act: -0.1700
Data Index: 8711058 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.4557. Min Act: -0.1700
Data Index: 3108383 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.4244. Min Act: -0.1700
Data Index: 5340822 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.3307. Min Act: -0.1700
Data Index: 7952003 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.3307. Min Act: -0.1700
Data Index: 8499414 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.3307. Min Act: -0.1700
Data Index: 327726 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.2994. Min Act: -0.1700
Data Index: 4634376 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.2682. Min Act: -0.1700
Data Index: 7816813 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.2057. Min Act: -0.1700
Data Index: 327728 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.1744. Min Act: -0.1700
Data Index: 8788046 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.1744. Min Act: -0.1700
Data Index: 2892855 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.1744. Min Act: -0.1700
Data Index: 5027750 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.1744. Min Act: -0.1700
Data Index: 4312750 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.1744. Min Act: -0.1700
Data Index: 5361507 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.1744. Min Act: -0.1700
Data Index: 3888258 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.0807. Min Act: -0.1700
Data Index: 7208100 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7369. Min Range: -8.7369
Max Act: 7.0807. Min Act: -0.1700
Data Index: 1819507 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19