Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.7621. Min Act: -0.1700
Data Index: 1854515 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.7934. Min Act: -0.1700
Data Index: 7457614 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.7309. Min Act: -0.1700
Data Index: 8768730 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.7621. Min Act: -0.1700
Data Index: 4049898 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.6684. Min Act: -0.1700
Data Index: 2140871 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.6059. Min Act: -0.1700
Data Index: 7754741 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.6059. Min Act: -0.1700
Data Index: 5216864 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.6059. Min Act: -0.1700
Data Index: 35923 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.5746. Min Act: -0.1700
Data Index: 3549674 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.6059. Min Act: -0.1700
Data Index: 3135707 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.6059. Min Act: -0.1700
Data Index: 6666580 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.6059. Min Act: -0.1700
Data Index: 5706800 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.6059. Min Act: -0.1700
Data Index: 3989156 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.5746. Min Act: -0.1700
Data Index: 7919223 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.5746. Min Act: -0.1700
Data Index: 5037663 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.5746. Min Act: -0.1700
Data Index: 8776217 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.5434. Min Act: -0.1700
Data Index: 6875631 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.5434. Min Act: -0.1700
Data Index: 1021954 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.5434. Min Act: -0.1700
Data Index: 7530131 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7934. Min Range: -5.7934
Max Act: 5.5746. Min Act: -0.1700
Data Index: 1748665 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19