Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.7074. Min Act: -0.1700
Data Index: 434965 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.5824. Min Act: -0.1700
Data Index: 518043 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.5199. Min Act: -0.1700
Data Index: 5847286 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.5199. Min Act: -0.1700
Data Index: 822149 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.4574. Min Act: -0.1700
Data Index: 4456505 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.3324. Min Act: -0.1700
Data Index: 2314433 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.3324. Min Act: -0.1700
Data Index: 1682773 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.2699. Min Act: -0.1700
Data Index: 4529689 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.2699. Min Act: -0.1700
Data Index: 5010260 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.2074. Min Act: -0.1700
Data Index: 880926 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.2074. Min Act: -0.1700
Data Index: 1284483 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.1449. Min Act: -0.1700
Data Index: 412840 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.0824. Min Act: -0.1700
Data Index: 3710031 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.1449. Min Act: -0.1700
Data Index: 3291403 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.1449. Min Act: -0.1700
Data Index: 4660434 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.0824. Min Act: -0.1700
Data Index: 7649218 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.0824. Min Act: -0.1700
Data Index: 6782290 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.0824. Min Act: -0.1700
Data Index: 2916043 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.0824. Min Act: -0.1700
Data Index: 146020 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7074. Min Range: -9.7074
Max Act: 9.0199. Min Act: -0.1700
Data Index: 5368365 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19