Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 97 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.9969. Min Act: -0.1700
Data Index: 845869 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.8225. Min Act: -0.1699
Data Index: 362260 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.7747. Min Act: -0.1700
Data Index: 1046286 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.7587. Min Act: -0.1700
Data Index: 667861 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.7747. Min Act: -0.1700
Data Index: 724963 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.7108. Min Act: -0.1700
Data Index: 753281 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.7268. Min Act: -0.1700
Data Index: 250165 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.7428. Min Act: -0.1700
Data Index: 1084130 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6948. Min Act: -0.1700
Data Index: 545869 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6948. Min Act: -0.1700
Data Index: 127122 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6948. Min Act: -0.1700
Data Index: 592283 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6948. Min Act: -0.1700
Data Index: 117390 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6948. Min Act: -0.1700
Data Index: 1197671 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6628. Min Act: -0.1700
Data Index: 72034 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6628. Min Act: -0.1700
Data Index: 870208 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6467. Min Act: -0.1700
Data Index: 1062269 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6628. Min Act: -0.1700
Data Index: 16400 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6307. Min Act: -0.1700
Data Index: 500940 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6467. Min Act: -0.1700
Data Index: 542280 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9969. Min Range: -2.9969
Max Act: 2.6467. Min Act: -0.1700
Data Index: 102195 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19