Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1222 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.6538. Min Act: -0.1700
Data Index: 114783 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5734. Min Act: -0.1700
Data Index: 462050 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5734. Min Act: -0.1700
Data Index: 866611 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5411. Min Act: -0.1700
Data Index: 416890 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5411. Min Act: -0.1700
Data Index: 797861 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.5088. Min Act: -0.1700
Data Index: 278869 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4602. Min Act: -0.1700
Data Index: 1242450 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4602. Min Act: -0.1700
Data Index: 577100 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4276. Min Act: -0.1700
Data Index: 783525 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4114. Min Act: -0.1700
Data Index: 1183771 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4114. Min Act: -0.1700
Data Index: 821023 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.4114. Min Act: -0.1700
Data Index: 237565 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.3951. Min Act: -0.1700
Data Index: 1110657 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.3951. Min Act: -0.1700
Data Index: 497593 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.3624. Min Act: -0.1700
Data Index: 927914 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.3460. Min Act: -0.1700
Data Index: 167202 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.3460. Min Act: -0.1700
Data Index: 16127 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.3460. Min Act: -0.1700
Data Index: 91790 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.3460. Min Act: -0.1700
Data Index: 249389 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6538. Min Range: -2.6538
Max Act: 2.3296. Min Act: -0.1700
Data Index: 432709 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19