Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2451 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.5747. Min Act: -0.1700
Data Index: 3686902 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.4810. Min Act: -0.1700
Data Index: 7754107 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.4185. Min Act: -0.1700
Data Index: 6738168 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.4497. Min Act: -0.1700
Data Index: 8345671 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.3872. Min Act: -0.1700
Data Index: 6606252 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.3872. Min Act: -0.1700
Data Index: 5702605 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.3247. Min Act: -0.1700
Data Index: 7401574 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2935. Min Act: -0.1700
Data Index: 3340321 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2935. Min Act: -0.1700
Data Index: 6866923 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2935. Min Act: -0.1700
Data Index: 688659 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2935. Min Act: -0.1700
Data Index: 6509835 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2622. Min Act: -0.1700
Data Index: 5170718 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2622. Min Act: -0.1700
Data Index: 1102819 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2935. Min Act: -0.1700
Data Index: 4680313 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2935. Min Act: -0.1700
Data Index: 8385043 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2935. Min Act: -0.1700
Data Index: 2585784 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2622. Min Act: -0.1700
Data Index: 1615383 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2622. Min Act: -0.1700
Data Index: 8409060 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2622. Min Act: -0.1700
Data Index: 4868358 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5747. Min Range: -5.5747
Max Act: 5.2622. Min Act: -0.1700
Data Index: 1630399 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19