Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1900 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.7043. Min Act: -0.1700
Data Index: 804191 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.6723. Min Act: -0.1700
Data Index: 681363 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.6562. Min Act: -0.1700
Data Index: 1156577 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.6562. Min Act: -0.1700
Data Index: 511435 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.6402. Min Act: -0.1700
Data Index: 1094350 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.6241. Min Act: -0.1700
Data Index: 962035 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.6081. Min Act: -0.1700
Data Index: 1265827 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.5920. Min Act: -0.1700
Data Index: 717112 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.5759. Min Act: -0.1700
Data Index: 107210 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.5759. Min Act: -0.1700
Data Index: 485724 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.5436. Min Act: -0.1700
Data Index: 586016 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.5597. Min Act: -0.1700
Data Index: 702027 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.5436. Min Act: -0.1700
Data Index: 1204442 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.5274. Min Act: -0.1700
Data Index: 356754 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.5113. Min Act: -0.1700
Data Index: 904890 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.4951. Min Act: -0.1700
Data Index: 1051048 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.4951. Min Act: -0.1700
Data Index: 1094165 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.4626. Min Act: -0.1700
Data Index: 576112 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.4301. Min Act: -0.1700
Data Index: 1188011 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7043. Min Range: -2.7043
Max Act: 2.4138. Min Act: -0.1700
Data Index: 1650082 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19