Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.4010. Min Act: -0.1700
Data Index: 1050966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.3481. Min Act: -0.1690
Data Index: 950683 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.2423. Min Act: -0.1700
Data Index: 317725 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.2423. Min Act: -0.1700
Data Index: 5130706 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.2423. Min Act: -0.1682
Data Index: 6106737 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.2423. Min Act: -0.1700
Data Index: 4034326 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.2423. Min Act: -0.1700
Data Index: 3288312 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.1718. Min Act: -0.1700
Data Index: 2137431 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.1367. Min Act: -0.1700
Data Index: 1343714 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.1367. Min Act: -0.1700
Data Index: 4665032 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.1191. Min Act: -0.1700
Data Index: 4867729 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.1103. Min Act: -0.1700
Data Index: 8369603 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.0928. Min Act: -0.1697
Data Index: 4957186 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.0928. Min Act: -0.1700
Data Index: 8068922 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.0928. Min Act: -0.1700
Data Index: 898389 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.0928. Min Act: -0.1700
Data Index: 966359 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.0928. Min Act: -0.1700
Data Index: 5044164 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.0928. Min Act: -0.1700
Data Index: 4125999 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.0841. Min Act: -0.1699
Data Index: 4892216 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4010. Min Range: -1.4010
Max Act: 1.0841. Min Act: -0.1700
Data Index: 5632846 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19