Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2011 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0232. Min Range: -3.0232
Max Act: 3.0232. Min Act: -0.1700
Data Index: 1214553 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.9916. Min Act: -0.1700
Data Index: 673624 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.9600. Min Act: -0.1700
Data Index: 584482 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.9441. Min Act: -0.1700
Data Index: 806021 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.9600. Min Act: -0.1700
Data Index: 497689 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.9124. Min Act: -0.1700
Data Index: 755114 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8648. Min Act: -0.1700
Data Index: 758874 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8489. Min Act: -0.1700
Data Index: 1136922 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8330. Min Act: -0.1700
Data Index: 478228 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8171. Min Act: -0.1700
Data Index: 947625 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8330. Min Act: -0.1700
Data Index: 186220 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8171. Min Act: -0.1700
Data Index: 87133 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8171. Min Act: -0.1700
Data Index: 149565 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8171. Min Act: -0.1700
Data Index: 886110 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8171. Min Act: -0.1700
Data Index: 93262 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8012. Min Act: -0.1700
Data Index: 124920 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8012. Min Act: -0.1700
Data Index: 601943 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8012. Min Act: -0.1700
Data Index: 654638 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.8012. Min Act: -0.1700
Data Index: 268711 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0232. Min Range: -3.0232
Max Act: 2.7853. Min Act: -0.1700
Data Index: 276314 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19