Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 139 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.6988. Min Act: -0.1700
Data Index: 1169148 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.5112. Min Act: -0.1700
Data Index: 788046 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.4487. Min Act: -0.1700
Data Index: 1327726 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.4175. Min Act: -0.1700
Data Index: 1328051 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.3550. Min Act: -0.1700
Data Index: 484725 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2612. Min Act: -0.1700
Data Index: 90716 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2925. Min Act: -0.1700
Data Index: 354305 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2925. Min Act: -0.1700
Data Index: 668597 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2925. Min Act: -0.1700
Data Index: 1048911 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2612. Min Act: -0.1700
Data Index: 361628 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.1987. Min Act: -0.1700
Data Index: 1063708 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2300. Min Act: -0.1700
Data Index: 398781 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.1987. Min Act: -0.1700
Data Index: 1071690 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2300. Min Act: -0.1700
Data Index: 499022 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2300. Min Act: -0.1700
Data Index: 467429 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2612. Min Act: -0.1700
Data Index: 1206929 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.2612. Min Act: -0.1700
Data Index: 562169 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.1987. Min Act: -0.1700
Data Index: 925308 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.1674. Min Act: -0.1700
Data Index: 1212307 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6988. Min Range: -4.6988
Max Act: 4.1987. Min Act: -0.1700
Data Index: 7781 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19