Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2039 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.4686. Min Act: -0.1700
Data Index: 1140729 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.3546. Min Act: -0.1700
Data Index: 1003096 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.3382. Min Act: -0.1700
Data Index: 1107072 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.3382. Min Act: -0.1700
Data Index: 447204 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.3218. Min Act: -0.1700
Data Index: 190658 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.3054. Min Act: -0.1700
Data Index: 556667 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.3054. Min Act: -0.1700
Data Index: 445220 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.3054. Min Act: -0.1700
Data Index: 1310920 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2889. Min Act: -0.1700
Data Index: 1193758 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2724. Min Act: -0.1700
Data Index: 684533 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2724. Min Act: -0.1700
Data Index: 896114 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2724. Min Act: -0.1700
Data Index: 320352 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2559. Min Act: -0.1700
Data Index: 1013449 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2559. Min Act: -0.1700
Data Index: 423538 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2559. Min Act: -0.1700
Data Index: 321082 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2394. Min Act: -0.1700
Data Index: 1113726 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2394. Min Act: -0.1700
Data Index: 830039 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2559. Min Act: -0.1700
Data Index: 981721 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2394. Min Act: -0.1700
Data Index: 1127496 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4686. Min Range: -2.4686
Max Act: 2.2394. Min Act: -0.1700
Data Index: 384137 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19