Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5898 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.8929. Min Act: -0.1700
Data Index: 2084643 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.6429. Min Act: -0.1700
Data Index: 569281 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.5804. Min Act: -0.1700
Data Index: 6990949 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.5804. Min Act: -0.1700
Data Index: 3549010 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.5492. Min Act: -0.1700
Data Index: 4304623 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.5179. Min Act: -0.1700
Data Index: 3288672 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.4867. Min Act: -0.1700
Data Index: 6636936 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.3304. Min Act: -0.1700
Data Index: 619479 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.3304. Min Act: -0.1700
Data Index: 2888479 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.3304. Min Act: -0.1700
Data Index: 3640235 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2992. Min Act: -0.1700
Data Index: 3235844 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2679. Min Act: -0.1700
Data Index: 8267887 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2992. Min Act: -0.1700
Data Index: 6311196 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2992. Min Act: -0.1700
Data Index: 7750731 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2679. Min Act: -0.1700
Data Index: 4138334 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2679. Min Act: -0.1700
Data Index: 1993545 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2679. Min Act: -0.1700
Data Index: 1946355 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2367. Min Act: -0.1700
Data Index: 7059293 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2367. Min Act: -0.1700
Data Index: 5502536 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8929. Min Range: -6.8929
Max Act: 6.2367. Min Act: -0.1700
Data Index: 5291955 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19