Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2024 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.4943. Min Act: -0.1700
Data Index: 37367 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.4619. Min Act: -0.1700
Data Index: 396447 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.4131. Min Act: -0.1700
Data Index: 101912 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3804. Min Act: -0.1700
Data Index: 315747 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3968. Min Act: -0.1700
Data Index: 1018591 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3804. Min Act: -0.1700
Data Index: 619870 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3804. Min Act: -0.1700
Data Index: 762780 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3968. Min Act: -0.1700
Data Index: 9790 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3804. Min Act: -0.1700
Data Index: 993050 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3804. Min Act: -0.1700
Data Index: 254082 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3804. Min Act: -0.1700
Data Index: 1328891 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3477. Min Act: -0.1700
Data Index: 337557 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3477. Min Act: -0.1700
Data Index: 218266 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3641. Min Act: -0.1700
Data Index: 784564 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3477. Min Act: -0.1700
Data Index: 757871 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3477. Min Act: -0.1700
Data Index: 550704 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3477. Min Act: -0.1700
Data Index: 937429 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3313. Min Act: -0.1700
Data Index: 721866 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3477. Min Act: -0.1700
Data Index: 675779 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4943. Min Range: -2.4943
Max Act: 2.3477. Min Act: -0.1700
Data Index: 282281 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19