Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1065 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.3666. Min Act: -0.1700
Data Index: 902475 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.4291. Min Act: -0.1700
Data Index: 1088727 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.3041. Min Act: -0.1700
Data Index: 1293279 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2728. Min Act: -0.1700
Data Index: 228663 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.3978. Min Act: -0.1700
Data Index: 1306560 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2728. Min Act: -0.1700
Data Index: 415192 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2728. Min Act: -0.1700
Data Index: 1314667 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.3041. Min Act: -0.1700
Data Index: 197999 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.3353. Min Act: -0.1700
Data Index: 1341668 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2103. Min Act: -0.1700
Data Index: 730077 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.3666. Min Act: -0.1700
Data Index: 841093 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2728. Min Act: -0.1700
Data Index: 597363 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2728. Min Act: -0.1700
Data Index: 149160 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.3041. Min Act: -0.1700
Data Index: 293284 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2103. Min Act: -0.1700
Data Index: 268682 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2103. Min Act: -0.1700
Data Index: 1017712 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.2416. Min Act: -0.1700
Data Index: 956907 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.1791. Min Act: -0.1700
Data Index: 1190694 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.1791. Min Act: -0.1700
Data Index: 551725 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4291. Min Range: -6.4291
Max Act: 6.1791. Min Act: -0.1700
Data Index: 180398 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19