Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 672 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.6386. Min Act: -0.1700
Data Index: 1310673 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.7325. Min Act: -0.1700
Data Index: 431262 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.6073. Min Act: -0.1700
Data Index: 45540 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.6699. Min Act: -0.1700
Data Index: 548995 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.6073. Min Act: -0.1700
Data Index: 646841 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.6699. Min Act: -0.1700
Data Index: 1269564 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.6073. Min Act: -0.1700
Data Index: 1291018 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.5446. Min Act: -0.1700
Data Index: 990828 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.5446. Min Act: -0.1700
Data Index: 1149417 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.5446. Min Act: -0.1700
Data Index: 1130203 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.5446. Min Act: -0.1700
Data Index: 1142236 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.5446. Min Act: -0.1700
Data Index: 793477 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.5760. Min Act: -0.1700
Data Index: 758173 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.4820. Min Act: -0.1700
Data Index: 215015 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.4820. Min Act: -0.1700
Data Index: 1124145 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.4820. Min Act: -0.1700
Data Index: 531742 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.4820. Min Act: -0.1700
Data Index: 878103 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.5133. Min Act: -0.1700
Data Index: 411239 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.4820. Min Act: -0.1700
Data Index: 988056 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7325. Min Range: -3.7325
Max Act: 3.5133. Min Act: -0.1700
Data Index: 1209165 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19