Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 932 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.3963. Min Act: -0.1700
Data Index: 1023502 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.2980. Min Act: -0.1700
Data Index: 378944 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.2816. Min Act: -0.1700
Data Index: 192609 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.2651. Min Act: -0.1700
Data Index: 1336802 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.1823. Min Act: -0.1700
Data Index: 1175533 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.1823. Min Act: -0.1700
Data Index: 1142628 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.1657. Min Act: -0.1700
Data Index: 786231 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.1657. Min Act: -0.1700
Data Index: 26120 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.1491. Min Act: -0.1700
Data Index: 245031 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.1491. Min Act: -0.1700
Data Index: 777403 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.1324. Min Act: -0.1700
Data Index: 758548 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.1157. Min Act: -0.1699
Data Index: 621074 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.1157. Min Act: -0.1700
Data Index: 741464 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.0990. Min Act: -0.1700
Data Index: 277327 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.0990. Min Act: -0.1700
Data Index: 1234927 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.0990. Min Act: -0.1700
Data Index: 215278 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.0822. Min Act: -0.1700
Data Index: 259721 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.0655. Min Act: -0.1700
Data Index: 796876 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.0655. Min Act: -0.1700
Data Index: 652657 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3963. Min Range: -2.3963
Max Act: 2.0571. Min Act: -0.1700
Data Index: 893131 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19