Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 98 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4965. Min Act: -0.1700
Data Index: 1130910 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4965. Min Act: -0.1700
Data Index: 1547354 (Python Code)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4965. Min Act: -0.1700
Data Index: 1358023 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.5127. Min Act: -0.1700
Data Index: 730550 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4803. Min Act: -0.1700
Data Index: 322383 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4641. Min Act: -0.1700
Data Index: 1610391 (Python Code)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4641. Min Act: -0.1700
Data Index: 1484410 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4641. Min Act: -0.1700
Data Index: 216705 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4478. Min Act: -0.1700
Data Index: 257988 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4478. Min Act: -0.1700
Data Index: 1656081 (Python Code)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4478. Min Act: -0.1700
Data Index: 554742 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4316. Min Act: -0.1700
Data Index: 1274691 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4478. Min Act: -0.1700
Data Index: 1238189 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4316. Min Act: -0.1700
Data Index: 516178 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4316. Min Act: -0.1700
Data Index: 958112 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4316. Min Act: -0.1700
Data Index: 910786 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4316. Min Act: -0.1700
Data Index: 227451 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4316. Min Act: -0.1700
Data Index: 1019392 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4316. Min Act: -0.1700
Data Index: 1653287 (Python Code)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5127. Min Range: -2.5127
Max Act: 2.4316. Min Act: -0.1700
Data Index: 499935 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19