Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 620 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6829. Min Range: -11.6829
Max Act: 11.6829. Min Act: -0.1700
Data Index: 1472175 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6829. Min Range: -11.6829
Max Act: 11.6204. Min Act: -0.1700
Data Index: 6858962 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6829. Min Range: -11.6829
Max Act: 11.4329. Min Act: -0.1700
Data Index: 7673182 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6829. Min Range: -11.6829
Max Act: 11.0579. Min Act: -0.1700
Data Index: 7305642 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6829. Min Range: -11.6829
Max Act: 11.0579. Min Act: -0.1700
Data Index: 2890056 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.9954. Min Act: -0.1700
Data Index: 5408141 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.8079. Min Act: -0.1700
Data Index: 6189981 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.6829. Min Act: -0.1700
Data Index: 8610492 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.6829. Min Act: -0.1700
Data Index: 5613083 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.6829. Min Act: -0.1700
Data Index: 2582687 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.6204. Min Act: -0.1700
Data Index: 1400741 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.6204. Min Act: -0.1700
Data Index: 6079070 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.5579. Min Act: -0.1700
Data Index: 5371271 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.4954. Min Act: -0.1700
Data Index: 8580200 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.4954. Min Act: -0.1700
Data Index: 7770195 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.4954. Min Act: -0.1700
Data Index: 3751316 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.4954. Min Act: -0.1700
Data Index: 5185036 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.4954. Min Act: -0.1700
Data Index: 7909943 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.4329. Min Act: -0.1700
Data Index: 3710647 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6829. Min Range: -11.6829
Max Act: 10.4329. Min Act: -0.1700
Data Index: 6047171 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19