Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1883 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.8820. Min Act: -0.1700
Data Index: 864858 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.6320. Min Act: -0.1700
Data Index: 720162 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.5695. Min Act: -0.1700
Data Index: 855350 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4445. Min Act: -0.1700
Data Index: 454706 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4757. Min Act: -0.1700
Data Index: 620890 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.5070. Min Act: -0.1700
Data Index: 924350 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.5070. Min Act: -0.1700
Data Index: 813226 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4757. Min Act: -0.1700
Data Index: 159128 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4445. Min Act: -0.1700
Data Index: 688221 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4445. Min Act: -0.1700
Data Index: 690102 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4445. Min Act: -0.1700
Data Index: 1154039 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4132. Min Act: -0.1700
Data Index: 862425 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4445. Min Act: -0.1700
Data Index: 63115 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4132. Min Act: -0.1700
Data Index: 93735 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4132. Min Act: -0.1700
Data Index: 902968 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4445. Min Act: -0.1700
Data Index: 731183 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.3819. Min Act: -0.1700
Data Index: 772947 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.4445. Min Act: -0.1700
Data Index: 340900 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.3819. Min Act: -0.1700
Data Index: 120688 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8820. Min Range: -4.8820
Max Act: 4.3819. Min Act: -0.1700
Data Index: 657521 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19