Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 994 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.4532. Min Act: -0.1700
Data Index: 777595 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.4369. Min Act: -0.1700
Data Index: 344646 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.4043. Min Act: -0.1700
Data Index: 1232036 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3717. Min Act: -0.1700
Data Index: 919683 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3880. Min Act: -0.1700
Data Index: 1155953 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3717. Min Act: -0.1700
Data Index: 566273 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3553. Min Act: -0.1700
Data Index: 126625 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3553. Min Act: -0.1700
Data Index: 1493786 (Python Code)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3553. Min Act: -0.1700
Data Index: 1140401 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3390. Min Act: -0.1700
Data Index: 364945 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3390. Min Act: -0.1700
Data Index: 1584291 (Python Code)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3226. Min Act: -0.1700
Data Index: 924117 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3226. Min Act: -0.1700
Data Index: 956263 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3226. Min Act: -0.1700
Data Index: 1330294 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3061. Min Act: -0.1700
Data Index: 1224118 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3226. Min Act: -0.1700
Data Index: 44412 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3061. Min Act: -0.1700
Data Index: 324985 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3226. Min Act: -0.1700
Data Index: 40683 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.2897. Min Act: -0.1700
Data Index: 273959 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4532. Min Range: -2.4532
Max Act: 2.3061. Min Act: -0.1700
Data Index: 1532693 (Python Code)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19