Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1920 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.8315. Min Act: -0.1700
Data Index: 162946 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.7997. Min Act: -0.1700
Data Index: 727399 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.7678. Min Act: -0.1700
Data Index: 1310801 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.7519. Min Act: -0.1700
Data Index: 105182 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.6879. Min Act: -0.1700
Data Index: 838301 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.7199. Min Act: -0.1700
Data Index: 1256480 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.6719. Min Act: -0.1700
Data Index: 240099 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.6398. Min Act: -0.1700
Data Index: 1210279 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.6077. Min Act: -0.1700
Data Index: 785734 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.6559. Min Act: -0.1700
Data Index: 131301 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.6398. Min Act: -0.1700
Data Index: 262079 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.6398. Min Act: -0.1700
Data Index: 613820 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.6077. Min Act: -0.1700
Data Index: 39023 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.6077. Min Act: -0.1700
Data Index: 315340 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.5594. Min Act: -0.1700
Data Index: 706838 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.5755. Min Act: -0.1700
Data Index: 694230 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.5755. Min Act: -0.1700
Data Index: 622401 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.5755. Min Act: -0.1700
Data Index: 1240850 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.5594. Min Act: -0.1700
Data Index: 1224191 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8315. Min Range: -2.8315
Max Act: 2.5594. Min Act: -0.1700
Data Index: 989967 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19