Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 88 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7957. Min Act: -0.1700
Data Index: 1518853 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7798. Min Act: -0.1700
Data Index: 1188464 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7798. Min Act: -0.1700
Data Index: 950319 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7479. Min Act: -0.1700
Data Index: 1142923 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7479. Min Act: -0.1700
Data Index: 1091949 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7319. Min Act: -0.1700
Data Index: 1094589 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7479. Min Act: -0.1700
Data Index: 136063 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7479. Min Act: -0.1700
Data Index: 1406876 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7319. Min Act: -0.1700
Data Index: 1589547 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7159. Min Act: -0.1700
Data Index: 217164 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7159. Min Act: -0.1700
Data Index: 1301616 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.6839. Min Act: -0.1700
Data Index: 1579123 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.6679. Min Act: -0.1700
Data Index: 1425092 (Python Code)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7159. Min Act: -0.1700
Data Index: 1420267 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.6999. Min Act: -0.1700
Data Index: 1074536 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.6999. Min Act: -0.1700
Data Index: 1011708 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.7159. Min Act: -0.1700
Data Index: 479730 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.6839. Min Act: -0.1700
Data Index: 865201 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.6999. Min Act: -0.1700
Data Index: 1178278 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7957. Min Range: -2.7957
Max Act: 2.6999. Min Act: -0.1700
Data Index: 516548 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19