Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 217 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.2910. Min Range: -5.2910
Max Act: 5.2910. Min Act: -0.1700
Data Index: 1101083 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.8847. Min Act: -0.1700
Data Index: 108128 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.8847. Min Act: -0.1700
Data Index: 894714 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.7910. Min Act: -0.1700
Data Index: 323789 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.7910. Min Act: -0.1700
Data Index: 575392 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.7597. Min Act: -0.1700
Data Index: 1356999 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.7597. Min Act: -0.1700
Data Index: 617255 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.6660. Min Act: -0.1700
Data Index: 1270604 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.6972. Min Act: -0.1700
Data Index: 1316740 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.6035. Min Act: -0.1700
Data Index: 589731 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.6660. Min Act: -0.1700
Data Index: 1331162 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.5722. Min Act: -0.1700
Data Index: 505210 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.5722. Min Act: -0.1700
Data Index: 1108110 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.6035. Min Act: -0.1700
Data Index: 1495570 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.6035. Min Act: -0.1700
Data Index: 1183948 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.6035. Min Act: -0.1700
Data Index: 744873 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.5410. Min Act: -0.1700
Data Index: 621064 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.5722. Min Act: -0.1700
Data Index: 777938 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.5722. Min Act: -0.1700
Data Index: 539858 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2910. Min Range: -5.2910
Max Act: 4.6035. Min Act: -0.1700
Data Index: 663843 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19