Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 203 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.3264. Min Act: -0.1700
Data Index: 881412 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.2771. Min Act: -0.1700
Data Index: 203594 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.2606. Min Act: -0.1700
Data Index: 1115349 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.2606. Min Act: -0.1700
Data Index: 481072 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.2441. Min Act: -0.1700
Data Index: 1286361 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.2606. Min Act: -0.1700
Data Index: 169685 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.2276. Min Act: -0.1700
Data Index: 663380 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.2110. Min Act: -0.1700
Data Index: 246909 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1944. Min Act: -0.1700
Data Index: 492832 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1944. Min Act: -0.1700
Data Index: 18591 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1778. Min Act: -0.1700
Data Index: 439276 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1529. Min Act: -0.1700
Data Index: 215192 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1778. Min Act: -0.1700
Data Index: 182670 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1612. Min Act: -0.1700
Data Index: 520172 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1612. Min Act: -0.1700
Data Index: 1170497 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1279. Min Act: -0.1700
Data Index: 288884 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1362. Min Act: -0.1700
Data Index: 1061485 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1529. Min Act: -0.1700
Data Index: 1070803 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1445. Min Act: -0.1700
Data Index: 1102389 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3264. Min Range: -2.3264
Max Act: 2.1362. Min Act: -0.1700
Data Index: 407052 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19