Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2037 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.9565. Min Act: -0.1700
Data Index: 566081 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.9565. Min Act: -0.1700
Data Index: 599412 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.9090. Min Act: -0.1700
Data Index: 72698 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.9248. Min Act: -0.1700
Data Index: 159124 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8931. Min Act: -0.1700
Data Index: 651560 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.9090. Min Act: -0.1700
Data Index: 372431 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8931. Min Act: -0.1700
Data Index: 1162246 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8931. Min Act: -0.1700
Data Index: 954734 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8772. Min Act: -0.1700
Data Index: 1272224 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8931. Min Act: -0.1700
Data Index: 377949 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8931. Min Act: -0.1700
Data Index: 221487 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8772. Min Act: -0.1700
Data Index: 1094909 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8772. Min Act: -0.1700
Data Index: 1280654 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8613. Min Act: -0.1700
Data Index: 1288704 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8772. Min Act: -0.1700
Data Index: 986607 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8772. Min Act: -0.1700
Data Index: 585442 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8772. Min Act: -0.1700
Data Index: 1023020 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8772. Min Act: -0.1700
Data Index: 674588 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8613. Min Act: -0.1700
Data Index: 199517 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9565. Min Range: -2.9565
Max Act: 2.8613. Min Act: -0.1700
Data Index: 1020618 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19