Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 23 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.7993. Min Act: -0.1700
Data Index: 1236111 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6875. Min Act: -0.1700
Data Index: 67924 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6875. Min Act: -0.1700
Data Index: 1537561 (Python Code)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6233. Min Act: -0.1700
Data Index: 284493 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6554. Min Act: -0.1700
Data Index: 1422445 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6554. Min Act: -0.1700
Data Index: 1429561 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6554. Min Act: -0.1700
Data Index: 1579699 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6233. Min Act: -0.1700
Data Index: 1245353 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6394. Min Act: -0.1700
Data Index: 977486 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6715. Min Act: -0.1700
Data Index: 848991 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6233. Min Act: -0.1700
Data Index: 550118 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6073. Min Act: -0.1700
Data Index: 1535302 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6394. Min Act: -0.1700
Data Index: 554155 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6073. Min Act: -0.1700
Data Index: 615146 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.5912. Min Act: -0.1700
Data Index: 1344174 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6233. Min Act: -0.1700
Data Index: 1580451 (Python Code)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6073. Min Act: -0.1700
Data Index: 1194528 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6073. Min Act: -0.1700
Data Index: 878753 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6073. Min Act: -0.1700
Data Index: 237260 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7993. Min Range: -2.7993
Max Act: 2.6233. Min Act: -0.1700
Data Index: 905229 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19