Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1905 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.5958. Min Act: -0.1700
Data Index: 1521930 (Python Code)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.4340. Min Act: -0.1700
Data Index: 1647831 (Python Code)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.4340. Min Act: -0.1700
Data Index: 506331 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.3688. Min Act: -0.1700
Data Index: 1428036 (Python Code)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.3524. Min Act: -0.1700
Data Index: 1334619 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.3360. Min Act: -0.1700
Data Index: 639927 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.3360. Min Act: -0.1700
Data Index: 227404 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2703. Min Act: -0.1700
Data Index: 925579 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2538. Min Act: -0.1700
Data Index: 369761 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2538. Min Act: -0.1700
Data Index: 907824 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2538. Min Act: -0.1700
Data Index: 1254618 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2372. Min Act: -0.1700
Data Index: 972429 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2372. Min Act: -0.1700
Data Index: 1088035 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2207. Min Act: -0.1700
Data Index: 195475 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2207. Min Act: -0.1700
Data Index: 530412 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2041. Min Act: -0.1700
Data Index: 1101325 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2041. Min Act: -0.1700
Data Index: 994512 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.2041. Min Act: -0.1700
Data Index: 1301952 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.1876. Min Act: -0.1700
Data Index: 304191 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5958. Min Range: -2.5958
Max Act: 2.1876. Min Act: -0.1700
Data Index: 1289693 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19