Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 699 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.5246. Min Act: -0.1700
Data Index: 1068261 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.4597. Min Act: -0.1700
Data Index: 439414 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.4435. Min Act: -0.1700
Data Index: 224895 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.4760. Min Act: -0.1700
Data Index: 1177395 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.4435. Min Act: -0.1700
Data Index: 220161 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.4109. Min Act: -0.1700
Data Index: 1096611 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.4109. Min Act: -0.1700
Data Index: 489521 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.4109. Min Act: -0.1700
Data Index: 188223 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3946. Min Act: -0.1700
Data Index: 1003559 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3783. Min Act: -0.1700
Data Index: 957760 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3620. Min Act: -0.1700
Data Index: 194289 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3620. Min Act: -0.1700
Data Index: 420109 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3620. Min Act: -0.1700
Data Index: 928822 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3620. Min Act: -0.1700
Data Index: 975870 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3620. Min Act: -0.1700
Data Index: 1137642 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3456. Min Act: -0.1700
Data Index: 270151 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3456. Min Act: -0.1700
Data Index: 620269 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3456. Min Act: -0.1700
Data Index: 72465 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3456. Min Act: -0.1700
Data Index: 1171342 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5246. Min Range: -2.5246
Max Act: 2.3292. Min Act: -0.1700
Data Index: 759306 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19