Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.8091. Min Act: -0.1700
Data Index: 1935403 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.8091. Min Act: -0.1700
Data Index: 4052993 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7466. Min Act: -0.1700
Data Index: 1812072 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7466. Min Act: -0.1700
Data Index: 1027772 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7153. Min Act: -0.1700
Data Index: 7483085 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7153. Min Act: -0.1700
Data Index: 6481392 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.7153. Min Act: -0.1700
Data Index: 2289293 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6841. Min Act: -0.1700
Data Index: 3118425 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6841. Min Act: -0.1700
Data Index: 4798406 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6528. Min Act: -0.1700
Data Index: 6637427 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6528. Min Act: -0.1700
Data Index: 6845608 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6528. Min Act: -0.1700
Data Index: 3519705 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6216. Min Act: -0.1700
Data Index: 8477301 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6216. Min Act: -0.1700
Data Index: 619257 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6216. Min Act: -0.1700
Data Index: 2478181 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6216. Min Act: -0.1700
Data Index: 8425561 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.6216. Min Act: -0.1700
Data Index: 7301942 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.5903. Min Act: -0.1700
Data Index: 6164157 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.5903. Min Act: -0.1700
Data Index: 2628743 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8091. Min Range: -5.8091
Max Act: 5.5903. Min Act: -0.1700
Data Index: 4201211 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19