Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1038 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4964. Min Range: -7.4964
Max Act: 7.4964. Min Act: -0.1700
Data Index: 5530668 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4964. Min Range: -7.4964
Max Act: 7.4652. Min Act: -0.1700
Data Index: 7711296 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4964. Min Range: -7.4964
Max Act: 7.3089. Min Act: -0.1700
Data Index: 8342290 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4964. Min Range: -7.4964
Max Act: 7.2777. Min Act: -0.1700
Data Index: 3438121 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4964. Min Range: -7.4964
Max Act: 7.0902. Min Act: -0.1700
Data Index: 8717961 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4964. Min Range: -7.4964
Max Act: 7.0902. Min Act: -0.1700
Data Index: 440572 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4964. Min Range: -7.4964
Max Act: 7.0277. Min Act: -0.1700
Data Index: 6974733 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4964. Min Range: -7.4964
Max Act: 7.0589. Min Act: -0.1700
Data Index: 1009921 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.9027. Min Act: -0.1700
Data Index: 5591690 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.8402. Min Act: -0.1700
Data Index: 1912045 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.8089. Min Act: -0.1700
Data Index: 4248457 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.8089. Min Act: -0.1700
Data Index: 1081185 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.8089. Min Act: -0.1700
Data Index: 1225397 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.7777. Min Act: -0.1700
Data Index: 3402716 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.8089. Min Act: -0.1700
Data Index: 342112 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.7777. Min Act: -0.1700
Data Index: 2681059 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.7777. Min Act: -0.1700
Data Index: 5770781 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.7464. Min Act: -0.1700
Data Index: 6166233 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.7152. Min Act: -0.1700
Data Index: 5276170 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4964. Min Range: -7.4964
Max Act: 6.6839. Min Act: -0.1700
Data Index: 5449219 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19