Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1956 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2074. Min Range: -6.2074
Max Act: 6.2074. Min Act: -0.1700
Data Index: 5280854 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2074. Min Range: -6.2074
Max Act: 6.1137. Min Act: -0.1700
Data Index: 1911163 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2074. Min Range: -6.2074
Max Act: 6.1137. Min Act: -0.1700
Data Index: 5542434 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2074. Min Range: -6.2074
Max Act: 6.0512. Min Act: -0.1700
Data Index: 5130217 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.9262. Min Act: -0.1700
Data Index: 4737459 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.8949. Min Act: -0.1700
Data Index: 4130106 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.8949. Min Act: -0.1700
Data Index: 6468368 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.8012. Min Act: -0.1700
Data Index: 1257284 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.8012. Min Act: -0.1700
Data Index: 7810785 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.7699. Min Act: -0.1700
Data Index: 3030954 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.7699. Min Act: -0.1700
Data Index: 5523323 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.7074. Min Act: -0.1700
Data Index: 1253454 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.7074. Min Act: -0.1700
Data Index: 3336257 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.7074. Min Act: -0.1700
Data Index: 1960712 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.6762. Min Act: -0.1700
Data Index: 8102325 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.6762. Min Act: -0.1700
Data Index: 7604202 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.6762. Min Act: -0.1700
Data Index: 4035182 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.6449. Min Act: -0.1700
Data Index: 6186091 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.6762. Min Act: -0.1700
Data Index: 4401168 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2074. Min Range: -6.2074
Max Act: 5.6762. Min Act: -0.1700
Data Index: 4270367 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19