Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 267 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.6137. Min Act: -0.1700
Data Index: 258428 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.5825. Min Act: -0.1700
Data Index: 631305 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.5512. Min Act: -0.1700
Data Index: 599646 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.5200. Min Act: -0.1700
Data Index: 938111 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.4887. Min Act: -0.1700
Data Index: 1129084 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.4887. Min Act: -0.1700
Data Index: 281421 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.4575. Min Act: -0.1700
Data Index: 75849 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.4575. Min Act: -0.1700
Data Index: 892803 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.3950. Min Act: -0.1700
Data Index: 1238187 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.4262. Min Act: -0.1700
Data Index: 1055635 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.4575. Min Act: -0.1700
Data Index: 92182 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.3950. Min Act: -0.1700
Data Index: 177889 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.4887. Min Act: -0.1700
Data Index: 775029 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.4262. Min Act: -0.1700
Data Index: 1180222 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.3950. Min Act: -0.1700
Data Index: 1169519 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.3012. Min Act: -0.1700
Data Index: 1306082 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.4262. Min Act: -0.1700
Data Index: 772953 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.3325. Min Act: -0.1700
Data Index: 790553 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.3012. Min Act: -0.1700
Data Index: 191631 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6137. Min Range: -4.6137
Max Act: 4.3325. Min Act: -0.1700
Data Index: 368042 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19