Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.8691. Min Act: -0.1700
Data Index: 7147311 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.8066. Min Act: -0.1700
Data Index: 6475785 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.7441. Min Act: -0.1700
Data Index: 1060878 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.7128. Min Act: -0.1700
Data Index: 3602348 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.6816. Min Act: -0.1700
Data Index: 6709244 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.6816. Min Act: -0.1700
Data Index: 4468914 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.6816. Min Act: -0.1700
Data Index: 5045591 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.6503. Min Act: -0.1700
Data Index: 1060885 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.6503. Min Act: -0.1700
Data Index: 1896530 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.6503. Min Act: -0.1700
Data Index: 2735524 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.6191. Min Act: -0.1700
Data Index: 2284138 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.5878. Min Act: -0.1700
Data Index: 8719970 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.5878. Min Act: -0.1700
Data Index: 2337056 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.5253. Min Act: -0.1700
Data Index: 5995221 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.5566. Min Act: -0.1700
Data Index: 5355188 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.5566. Min Act: -0.1700
Data Index: 21702 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.5878. Min Act: -0.1700
Data Index: 4892182 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.5878. Min Act: -0.1700
Data Index: 3153176 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.5566. Min Act: -0.1700
Data Index: 3528802 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8691. Min Range: -4.8691
Max Act: 4.5566. Min Act: -0.1700
Data Index: 2483448 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19