Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1023 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.2695. Min Range: -6.2695
Max Act: 6.2695. Min Act: -0.1700
Data Index: 964506 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.9570. Min Act: -0.1700
Data Index: 3958 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.8633. Min Act: -0.1700
Data Index: 1582873 (Python Code)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.8945. Min Act: -0.1700
Data Index: 1588089 (Python Code)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.8633. Min Act: -0.1700
Data Index: 162948 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.8945. Min Act: -0.1700
Data Index: 1421 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.8320. Min Act: -0.1700
Data Index: 1089707 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.6445. Min Act: -0.1700
Data Index: 928662 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.8008. Min Act: -0.1700
Data Index: 716404 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.7070. Min Act: -0.1700
Data Index: 1252656 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.7070. Min Act: -0.1700
Data Index: 802548 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.7070. Min Act: -0.1700
Data Index: 512700 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.6133. Min Act: -0.1700
Data Index: 115402 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.5820. Min Act: -0.1700
Data Index: 30221 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.6445. Min Act: -0.1700
Data Index: 1448792 (Python Code)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.6758. Min Act: -0.1700
Data Index: 1464649 (Python Code)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.5820. Min Act: -0.1700
Data Index: 501839 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.5195. Min Act: -0.1700
Data Index: 134225 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.6445. Min Act: -0.1700
Data Index: 1296799 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2695. Min Range: -6.2695
Max Act: 5.6445. Min Act: -0.1700
Data Index: 1289347 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19