Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1558 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.5940. Min Act: -0.1700
Data Index: 493836 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.5779. Min Act: -0.1700
Data Index: 358585 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.5779. Min Act: -0.1700
Data Index: 1296357 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.5779. Min Act: -0.1700
Data Index: 755177 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4809. Min Act: -0.1700
Data Index: 1133943 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4809. Min Act: -0.1700
Data Index: 9287 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4647. Min Act: -0.1700
Data Index: 1149319 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4647. Min Act: -0.1700
Data Index: 839370 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4647. Min Act: -0.1700
Data Index: 224788 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4485. Min Act: -0.1700
Data Index: 357059 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4647. Min Act: -0.1700
Data Index: 305395 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4647. Min Act: -0.1700
Data Index: 1177551 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4485. Min Act: -0.1700
Data Index: 1158244 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4322. Min Act: -0.1700
Data Index: 651978 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4485. Min Act: -0.1700
Data Index: 1301570 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4159. Min Act: -0.1700
Data Index: 324217 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4159. Min Act: -0.1700
Data Index: 368703 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4322. Min Act: -0.1700
Data Index: 1162249 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4322. Min Act: -0.1700
Data Index: 334102 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5940. Min Range: -2.5940
Max Act: 2.4159. Min Act: -0.1700
Data Index: 902347 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19