Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 138 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.2488. Min Act: -0.1700
Data Index: 471827 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.2157. Min Act: -0.1700
Data Index: 1233785 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.1826. Min Act: -0.1700
Data Index: 83152 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.1493. Min Act: -0.1700
Data Index: 231489 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.0489. Min Act: -0.1700
Data Index: 885196 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.0657. Min Act: -0.1700
Data Index: 614873 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.0657. Min Act: -0.1700
Data Index: 1063024 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.0321. Min Act: -0.1700
Data Index: 199150 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.0152. Min Act: -0.1700
Data Index: 1045110 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.0321. Min Act: -0.1700
Data Index: 1292301 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.0152. Min Act: -0.1700
Data Index: 328349 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2488. Min Range: -2.2488
Max Act: 2.0321. Min Act: -0.1700
Data Index: 464550 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2488. Min Range: -2.2488
Max Act: 1.9815. Min Act: -0.1700
Data Index: 295654 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2488. Min Range: -2.2488
Max Act: 1.9984. Min Act: -0.1700
Data Index: 318871 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2488. Min Range: -2.2488
Max Act: 1.9984. Min Act: -0.1700
Data Index: 765738 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2488. Min Range: -2.2488
Max Act: 1.9815. Min Act: -0.1700
Data Index: 450622 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2488. Min Range: -2.2488
Max Act: 1.9984. Min Act: -0.1700
Data Index: 937750 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2488. Min Range: -2.2488
Max Act: 1.9984. Min Act: -0.1700
Data Index: 1057570 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2488. Min Range: -2.2488
Max Act: 1.9815. Min Act: -0.1700
Data Index: 1020959 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2488. Min Range: -2.2488
Max Act: 1.9815. Min Act: -0.1700
Data Index: 103803 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19