Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1119 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.8940. Min Act: -0.1700
Data Index: 47024 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.9565. Min Act: -0.1700
Data Index: 140185 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.7690. Min Act: -0.1700
Data Index: 1154772 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.7378. Min Act: -0.1700
Data Index: 1253138 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.7378. Min Act: -0.1700
Data Index: 634014 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.8940. Min Act: -0.1700
Data Index: 1199055 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.8003. Min Act: -0.1700
Data Index: 186949 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.8628. Min Act: -0.1700
Data Index: 532533 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.8315. Min Act: -0.1700
Data Index: 787961 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.7378. Min Act: -0.1700
Data Index: 483337 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.7378. Min Act: -0.1700
Data Index: 24206 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.7065. Min Act: -0.1700
Data Index: 1335264 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.6440. Min Act: -0.1700
Data Index: 197211 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.5815. Min Act: -0.1700
Data Index: 850739 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.8003. Min Act: -0.1700
Data Index: 186860 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.7690. Min Act: -0.1700
Data Index: 108515 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.6440. Min Act: -0.1700
Data Index: 956940 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.6753. Min Act: -0.1700
Data Index: 1123438 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.6753. Min Act: -0.1700
Data Index: 468625 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9565. Min Range: -5.9565
Max Act: 5.7065. Min Act: -0.1700
Data Index: 747998 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19