Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2741 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.8619. Min Act: -0.1700
Data Index: 5871164 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.7369. Min Act: -0.1700
Data Index: 1611436 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.6744. Min Act: -0.1700
Data Index: 2912000 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.6744. Min Act: -0.1700
Data Index: 5906971 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.6744. Min Act: -0.1700
Data Index: 4096181 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.5494. Min Act: -0.1700
Data Index: 2516398 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.5181. Min Act: -0.1700
Data Index: 6182142 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.5181. Min Act: -0.1700
Data Index: 3733598 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.5181. Min Act: -0.1700
Data Index: 1578264 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.4869. Min Act: -0.1700
Data Index: 2333475 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.4869. Min Act: -0.1700
Data Index: 7711045 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.4556. Min Act: -0.1700
Data Index: 1181514 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.4556. Min Act: -0.1700
Data Index: 6159068 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.3931. Min Act: -0.1700
Data Index: 818984 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.4244. Min Act: -0.1700
Data Index: 6162933 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.3931. Min Act: -0.1700
Data Index: 2864475 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.3306. Min Act: -0.1700
Data Index: 799687 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.3306. Min Act: -0.1700
Data Index: 7227499 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.2994. Min Act: -0.1700
Data Index: 5312680 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8619. Min Range: -6.8619
Max Act: 6.2994. Min Act: -0.1700
Data Index: 8410095 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19