Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1994 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.5135. Min Act: -0.1700
Data Index: 261446 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.4649. Min Act: -0.1700
Data Index: 372080 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.4649. Min Act: -0.1700
Data Index: 1311591 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.4487. Min Act: -0.1700
Data Index: 708896 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.4487. Min Act: -0.1700
Data Index: 453826 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.4324. Min Act: -0.1700
Data Index: 1272155 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3998. Min Act: -0.1700
Data Index: 1549339 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3998. Min Act: -0.1700
Data Index: 1367997 (Python Code)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3835. Min Act: -0.1700
Data Index: 1595349 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3671. Min Act: -0.1700
Data Index: 1631098 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3508. Min Act: -0.1700
Data Index: 1645157 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3508. Min Act: -0.1700
Data Index: 1119816 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3671. Min Act: -0.1700
Data Index: 240754 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3508. Min Act: -0.1700
Data Index: 1176910 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3508. Min Act: -0.1700
Data Index: 1605002 (Python Code)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3508. Min Act: -0.1700
Data Index: 1496239 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3671. Min Act: -0.1700
Data Index: 1441386 (Python Code)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3344. Min Act: -0.1700
Data Index: 1441371 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3508. Min Act: -0.1700
Data Index: 1450718 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5135. Min Range: -2.5135
Max Act: 2.3344. Min Act: -0.1700
Data Index: 1439531 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19