Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2016 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0070. Min Range: -3.0070
Max Act: 3.0070. Min Act: -0.1700
Data Index: 902411 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0070. Min Range: -3.0070
Max Act: 3.0070. Min Act: -0.1700
Data Index: 295301 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.9437. Min Act: -0.1700
Data Index: 440961 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.9279. Min Act: -0.1700
Data Index: 1355972 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.9437. Min Act: -0.1700
Data Index: 1196530 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.9437. Min Act: -0.1700
Data Index: 1331311 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.9120. Min Act: -0.1700
Data Index: 200790 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8962. Min Act: -0.1700
Data Index: 865718 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.9120. Min Act: -0.1700
Data Index: 1337406 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8803. Min Act: -0.1700
Data Index: 1148457 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.9120. Min Act: -0.1700
Data Index: 1286086 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8803. Min Act: -0.1700
Data Index: 261760 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8644. Min Act: -0.1700
Data Index: 1298277 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8803. Min Act: -0.1700
Data Index: 1326292 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8644. Min Act: -0.1700
Data Index: 263283 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8644. Min Act: -0.1700
Data Index: 390678 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8485. Min Act: -0.1700
Data Index: 419237 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8644. Min Act: -0.1700
Data Index: 1174193 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8485. Min Act: -0.1700
Data Index: 168891 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0070. Min Range: -3.0070
Max Act: 2.8803. Min Act: -0.1700
Data Index: 827421 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19