Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1948 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.8209. Min Act: -0.1700
Data Index: 989460 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.8050. Min Act: -0.1700
Data Index: 765374 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.7093. Min Act: -0.1700
Data Index: 145470 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.7093. Min Act: -0.1700
Data Index: 360316 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6933. Min Act: -0.1700
Data Index: 606047 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6773. Min Act: -0.1700
Data Index: 255195 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6773. Min Act: -0.1700
Data Index: 492954 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6452. Min Act: -0.1700
Data Index: 895066 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6452. Min Act: -0.1700
Data Index: 277347 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6612. Min Act: -0.1700
Data Index: 1122391 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6452. Min Act: -0.1700
Data Index: 865830 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6452. Min Act: -0.1700
Data Index: 1257402 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6130. Min Act: -0.1700
Data Index: 1316123 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6291. Min Act: -0.1700
Data Index: 334688 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.6130. Min Act: -0.1700
Data Index: 1251697 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.5970. Min Act: -0.1700
Data Index: 572858 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.5970. Min Act: -0.1700
Data Index: 339516 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.5970. Min Act: -0.1700
Data Index: 311015 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.5970. Min Act: -0.1700
Data Index: 1017730 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8209. Min Range: -2.8209
Max Act: 2.5970. Min Act: -0.1700
Data Index: 1299879 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19