Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 255 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.9280. Min Act: -0.1700
Data Index: 701633 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.9121. Min Act: -0.1700
Data Index: 1018071 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.9121. Min Act: -0.1700
Data Index: 534493 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.9121. Min Act: -0.1700
Data Index: 116358 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.9121. Min Act: -0.1700
Data Index: 748325 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.9280. Min Act: -0.1700
Data Index: 1039948 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8645. Min Act: -0.1700
Data Index: 396115 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8962. Min Act: -0.1700
Data Index: 569311 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8804. Min Act: -0.1700
Data Index: 1188093 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8804. Min Act: -0.1700
Data Index: 342299 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8804. Min Act: -0.1700
Data Index: 435985 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8804. Min Act: -0.1700
Data Index: 1086580 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8804. Min Act: -0.1700
Data Index: 1105539 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8804. Min Act: -0.1700
Data Index: 775414 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8962. Min Act: -0.1700
Data Index: 812514 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8645. Min Act: -0.1700
Data Index: 1250350 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8804. Min Act: -0.1700
Data Index: 169714 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8804. Min Act: -0.1700
Data Index: 380189 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8804. Min Act: -0.1700
Data Index: 846316 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9280. Min Range: -2.9280
Max Act: 2.8645. Min Act: -0.1700
Data Index: 980492 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19