Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2036 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.4336. Min Act: -0.1700
Data Index: 241537 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3684. Min Act: -0.1700
Data Index: 571292 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3684. Min Act: -0.1700
Data Index: 1084725 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3520. Min Act: -0.1700
Data Index: 1028663 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3520. Min Act: -0.1700
Data Index: 623246 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3520. Min Act: -0.1700
Data Index: 1071705 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3356. Min Act: -0.1700
Data Index: 1285134 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3356. Min Act: -0.1700
Data Index: 115726 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3356. Min Act: -0.1700
Data Index: 166600 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3192. Min Act: -0.1700
Data Index: 197462 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3356. Min Act: -0.1700
Data Index: 1157006 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3356. Min Act: -0.1700
Data Index: 1070525 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3356. Min Act: -0.1700
Data Index: 157750 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3356. Min Act: -0.1700
Data Index: 420969 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3192. Min Act: -0.1700
Data Index: 630465 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3192. Min Act: -0.1700
Data Index: 923097 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3192. Min Act: -0.1700
Data Index: 1067380 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3356. Min Act: -0.1700
Data Index: 1226114 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3192. Min Act: -0.1700
Data Index: 6258 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4336. Min Range: -2.4336
Max Act: 2.3356. Min Act: -0.1700
Data Index: 1196796 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19