Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 191 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.8921. Min Act: -0.1700
Data Index: 219505 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.8921. Min Act: -0.1700
Data Index: 782427 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.8604. Min Act: -0.1700
Data Index: 1244557 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.8127. Min Act: -0.1700
Data Index: 644930 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.7968. Min Act: -0.1700
Data Index: 794591 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.7489. Min Act: -0.1700
Data Index: 71622 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.7329. Min Act: -0.1700
Data Index: 1026019 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.6850. Min Act: -0.1700
Data Index: 321973 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.6369. Min Act: -0.1700
Data Index: 959565 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.6369. Min Act: -0.1700
Data Index: 937576 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.5886. Min Act: -0.1700
Data Index: 7912 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.5725. Min Act: -0.1700
Data Index: 577761 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.5725. Min Act: -0.1700
Data Index: 9833 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.5725. Min Act: -0.1700
Data Index: 1010953 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.5402. Min Act: -0.1700
Data Index: 806249 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.5402. Min Act: -0.1700
Data Index: 887178 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.4755. Min Act: -0.1700
Data Index: 963577 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.4755. Min Act: -0.1700
Data Index: 573223 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.4430. Min Act: -0.1700
Data Index: 338187 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8921. Min Range: -2.8921
Max Act: 2.4430. Min Act: -0.1700
Data Index: 639117 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19