Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1918 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2769. Min Act: -0.1700
Data Index: 1390342 (Python Code)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2604. Min Act: -0.1700
Data Index: 317464 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2604. Min Act: -0.1700
Data Index: 240437 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2439. Min Act: -0.1700
Data Index: 1132116 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2439. Min Act: -0.1700
Data Index: 399219 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2439. Min Act: -0.1700
Data Index: 219668 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2274. Min Act: -0.1700
Data Index: 1079904 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2108. Min Act: -0.1700
Data Index: 964566 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2108. Min Act: -0.1700
Data Index: 712557 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2108. Min Act: -0.1700
Data Index: 357984 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.2108. Min Act: -0.1700
Data Index: 733526 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.1943. Min Act: -0.1700
Data Index: 24398 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.1943. Min Act: -0.1700
Data Index: 856886 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.1777. Min Act: -0.1700
Data Index: 815259 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.1943. Min Act: -0.1700
Data Index: 1154146 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.1943. Min Act: -0.1700
Data Index: 87838 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.1777. Min Act: -0.1700
Data Index: 1095642 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.1777. Min Act: -0.1700
Data Index: 697240 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.1943. Min Act: -0.1700
Data Index: 503567 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2769. Min Range: -2.2769
Max Act: 2.1777. Min Act: -0.1700
Data Index: 403834 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19