Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 813 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.6149. Min Act: -0.1700
Data Index: 1258000 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5182. Min Act: -0.1700
Data Index: 407988 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5182. Min Act: -0.1700
Data Index: 501677 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5182. Min Act: -0.1700
Data Index: 779160 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5020. Min Act: -0.1700
Data Index: 275521 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.5020. Min Act: -0.1700
Data Index: 876399 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4858. Min Act: -0.1700
Data Index: 426569 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4533. Min Act: -0.1700
Data Index: 292124 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4533. Min Act: -0.1700
Data Index: 774903 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4533. Min Act: -0.1700
Data Index: 1256617 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4533. Min Act: -0.1700
Data Index: 567968 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4533. Min Act: -0.1700
Data Index: 289335 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4371. Min Act: -0.1700
Data Index: 444221 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4371. Min Act: -0.1700
Data Index: 1355111 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4371. Min Act: -0.1700
Data Index: 548725 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4208. Min Act: -0.1700
Data Index: 6287 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4371. Min Act: -0.1700
Data Index: 784714 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4208. Min Act: -0.1700
Data Index: 354847 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4208. Min Act: -0.1700
Data Index: 121703 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6149. Min Range: -2.6149
Max Act: 2.4208. Min Act: -0.1700
Data Index: 1113209 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19