Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 938 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.3030. Min Act: -0.1700
Data Index: 315189 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2865. Min Act: -0.1700
Data Index: 302497 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2865. Min Act: -0.1700
Data Index: 423440 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2865. Min Act: -0.1700
Data Index: 477952 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2701. Min Act: -0.1700
Data Index: 210495 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2701. Min Act: -0.1700
Data Index: 205383 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2536. Min Act: -0.1700
Data Index: 998727 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2371. Min Act: -0.1700
Data Index: 373923 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2371. Min Act: -0.1700
Data Index: 1122888 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2536. Min Act: -0.1700
Data Index: 1110944 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2536. Min Act: -0.1700
Data Index: 181424 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2205. Min Act: -0.1700
Data Index: 1639058 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2371. Min Act: -0.1700
Data Index: 355885 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2205. Min Act: -0.1700
Data Index: 290254 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2205. Min Act: -0.1700
Data Index: 374959 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.1874. Min Act: -0.1700
Data Index: 14614 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2371. Min Act: -0.1700
Data Index: 647708 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.1708. Min Act: -0.1700
Data Index: 681176 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2205. Min Act: -0.1700
Data Index: 786895 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3030. Min Range: -2.3030
Max Act: 2.2040. Min Act: -0.1700
Data Index: 1504419 (Python Code)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19