Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 35 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.2757. Min Act: -0.1700
Data Index: 482272 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.2132. Min Act: -0.1700
Data Index: 1280362 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.1506. Min Act: -0.1700
Data Index: 429445 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0881. Min Act: -0.1700
Data Index: 871724 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0881. Min Act: -0.1700
Data Index: 117182 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0569. Min Act: -0.1700
Data Index: 830025 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0881. Min Act: -0.1700
Data Index: 185037 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0881. Min Act: -0.1700
Data Index: 526154 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0881. Min Act: -0.1700
Data Index: 212728 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0256. Min Act: -0.1700
Data Index: 1085173 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0256. Min Act: -0.1700
Data Index: 583199 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2757. Min Range: -4.2757
Max Act: 3.9943. Min Act: -0.1700
Data Index: 1161106 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2757. Min Range: -4.2757
Max Act: 3.9943. Min Act: -0.1700
Data Index: 1344094 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2757. Min Range: -4.2757
Max Act: 3.9943. Min Act: -0.1700
Data Index: 563926 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0569. Min Act: -0.1700
Data Index: 975420 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2757. Min Range: -4.2757
Max Act: 4.0256. Min Act: -0.1700
Data Index: 484986 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2757. Min Range: -4.2757
Max Act: 3.9943. Min Act: -0.1700
Data Index: 512670 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2757. Min Range: -4.2757
Max Act: 3.9943. Min Act: -0.1700
Data Index: 340305 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2757. Min Range: -4.2757
Max Act: 3.9943. Min Act: -0.1700
Data Index: 306523 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2757. Min Range: -4.2757
Max Act: 3.9943. Min Act: -0.1700
Data Index: 351472 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19