Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3690 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.3904. Min Act: -0.1700
Data Index: 8730085 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.2654. Min Act: -0.1700
Data Index: 7864159 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.2654. Min Act: -0.1700
Data Index: 1589919 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.2029. Min Act: -0.1700
Data Index: 3133108 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.1716. Min Act: -0.1700
Data Index: 3100290 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.2029. Min Act: -0.1700
Data Index: 1396693 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.1404. Min Act: -0.1700
Data Index: 5923878 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.1404. Min Act: -0.1700
Data Index: 2988029 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.1091. Min Act: -0.1700
Data Index: 6964214 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.1091. Min Act: -0.1700
Data Index: 6933971 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.0779. Min Act: -0.1700
Data Index: 3829376 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.0154. Min Act: -0.1700
Data Index: 3414086 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.0154. Min Act: -0.1700
Data Index: 118428 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.0154. Min Act: -0.1700
Data Index: 2936612 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3904. Min Range: -5.3904
Max Act: 5.0154. Min Act: -0.1700
Data Index: 4636881 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3904. Min Range: -5.3904
Max Act: 4.9841. Min Act: -0.1700
Data Index: 2729570 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3904. Min Range: -5.3904
Max Act: 4.9841. Min Act: -0.1700
Data Index: 2026393 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3904. Min Range: -5.3904
Max Act: 4.9529. Min Act: -0.1700
Data Index: 5154428 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3904. Min Range: -5.3904
Max Act: 4.9529. Min Act: -0.1700
Data Index: 6923055 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3904. Min Range: -5.3904
Max Act: 4.9529. Min Act: -0.1700
Data Index: 7541507 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19