Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.2141. Min Act: -0.1700
Data Index: 744582 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1809. Min Act: -0.1700
Data Index: 5292344 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1809. Min Act: -0.1700
Data Index: 8174130 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1809. Min Act: -0.1700
Data Index: 2959622 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1642. Min Act: -0.1700
Data Index: 3115054 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1642. Min Act: -0.1700
Data Index: 3576340 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1476. Min Act: -0.1700
Data Index: 4308412 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1642. Min Act: -0.1699
Data Index: 968864 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1809. Min Act: -0.1700
Data Index: 5501853 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1476. Min Act: -0.1691
Data Index: 6319440 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1476. Min Act: -0.1700
Data Index: 1986173 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1476. Min Act: -0.1700
Data Index: 721741 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1476. Min Act: -0.1700
Data Index: 2614733 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1309. Min Act: -0.1699
Data Index: 6314851 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1476. Min Act: -0.1700
Data Index: 7861191 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1309. Min Act: -0.1700
Data Index: 2196388 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1142. Min Act: -0.1700
Data Index: 5740912 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1142. Min Act: -0.1696
Data Index: 3627353 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.0974. Min Act: -0.1700
Data Index: 3966521 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2141. Min Range: -2.2141
Max Act: 2.1142. Min Act: -0.1700
Data Index: 5033959 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19