Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 200 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2545. Min Range: -3.2545
Max Act: 3.2545. Min Act: -0.1700
Data Index: 205306 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2545. Min Range: -3.2545
Max Act: 3.2073. Min Act: -0.1700
Data Index: 588130 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.9865. Min Act: -0.1700
Data Index: 632800 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.9549. Min Act: -0.1700
Data Index: 954367 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.9074. Min Act: -0.1700
Data Index: 1246742 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.9074. Min Act: -0.1700
Data Index: 831302 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.8915. Min Act: -0.1700
Data Index: 1073810 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.9074. Min Act: -0.1700
Data Index: 522613 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.8597. Min Act: -0.1700
Data Index: 551241 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.8120. Min Act: -0.1700
Data Index: 387961 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.8280. Min Act: -0.1700
Data Index: 197583 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.7642. Min Act: -0.1700
Data Index: 1294494 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.8120. Min Act: -0.1700
Data Index: 852570 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.7961. Min Act: -0.1700
Data Index: 438131 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.7961. Min Act: -0.1700
Data Index: 520229 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.7642. Min Act: -0.1700
Data Index: 971226 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.7802. Min Act: -0.1700
Data Index: 769828 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.7483. Min Act: -0.1700
Data Index: 1072989 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.7483. Min Act: -0.1700
Data Index: 301404 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2545. Min Range: -3.2545
Max Act: 2.7642. Min Act: -0.1700
Data Index: 787660 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19