Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2036 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.8947. Min Act: -0.1700
Data Index: 230308 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.5590. Min Act: -0.1700
Data Index: 255831 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.5590. Min Act: -0.1700
Data Index: 1626465 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.4943. Min Act: -0.1700
Data Index: 825189 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.4943. Min Act: -0.1700
Data Index: 1064737 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.4943. Min Act: -0.1700
Data Index: 974373 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.4943. Min Act: -0.1700
Data Index: 1630430 (Python Code)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.4619. Min Act: -0.1700
Data Index: 491295 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.4781. Min Act: -0.1700
Data Index: 90366 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.4294. Min Act: -0.1700
Data Index: 1445490 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.4294. Min Act: -0.1700
Data Index: 1551673 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.3968. Min Act: -0.1700
Data Index: 172367 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.3805. Min Act: -0.1700
Data Index: 149850 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.3968. Min Act: -0.1700
Data Index: 977430 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.3805. Min Act: -0.1700
Data Index: 1345038 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.3805. Min Act: -0.1700
Data Index: 431082 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.3478. Min Act: -0.1700
Data Index: 173872 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.3641. Min Act: -0.1700
Data Index: 415668 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.3478. Min Act: -0.1700
Data Index: 1446879 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8947. Min Range: -2.8947
Max Act: 2.3478. Min Act: -0.1700
Data Index: 871187 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19