Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1839 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.4547. Min Act: -0.1700
Data Index: 973528 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.4391. Min Act: -0.1700
Data Index: 64307 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.3292. Min Act: -0.1700
Data Index: 332688 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.3292. Min Act: -0.1700
Data Index: 514355 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2978. Min Act: -0.1700
Data Index: 51835 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.3135. Min Act: -0.1700
Data Index: 792781 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.3135. Min Act: -0.1700
Data Index: 1344684 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2978. Min Act: -0.1700
Data Index: 252795 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2350. Min Act: -0.1700
Data Index: 918117 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2978. Min Act: -0.1700
Data Index: 995245 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2664. Min Act: -0.1700
Data Index: 173424 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2978. Min Act: -0.1700
Data Index: 727646 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2507. Min Act: -0.1700
Data Index: 1331829 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2664. Min Act: -0.1700
Data Index: 468162 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2193. Min Act: -0.1700
Data Index: 954051 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2035. Min Act: -0.1700
Data Index: 356581 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2350. Min Act: -0.1700
Data Index: 169670 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2350. Min Act: -0.1700
Data Index: 260116 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2350. Min Act: -0.1700
Data Index: 1237581 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4547. Min Range: -3.4547
Max Act: 3.2507. Min Act: -0.1700
Data Index: 807601 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19