Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 76 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.4436. Min Range: -3.4436
Max Act: 3.4436. Min Act: -0.1700
Data Index: 1635120 (Python Code)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4436. Min Range: -3.4436
Max Act: 3.3965. Min Act: -0.1700
Data Index: 1616464 (Python Code)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4436. Min Range: -3.4436
Max Act: 3.3495. Min Act: -0.1700
Data Index: 1579419 (Python Code)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4436. Min Range: -3.4436
Max Act: 3.2867. Min Act: -0.1700
Data Index: 1568216 (Python Code)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4436. Min Range: -3.4436
Max Act: 3.2238. Min Act: -0.1700
Data Index: 1457192 (Python Code)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.9556. Min Act: -0.1700
Data Index: 1407110 (Python Code)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.9398. Min Act: -0.1700
Data Index: 1403102 (Python Code)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.9240. Min Act: -0.1700
Data Index: 1571213 (Python Code)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.9398. Min Act: -0.1700
Data Index: 1408788 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.9081. Min Act: -0.1700
Data Index: 1583563 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.8922. Min Act: -0.1700
Data Index: 1575009 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.8922. Min Act: -0.1700
Data Index: 1444946 (Python Code)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.8764. Min Act: -0.1700
Data Index: 1391909 (Python Code)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.9081. Min Act: -0.1700
Data Index: 1453557 (Python Code)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.8922. Min Act: -0.1700
Data Index: 826983 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.8764. Min Act: -0.1700
Data Index: 1502768 (Python Code)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.8764. Min Act: -0.1700
Data Index: 1535035 (Python Code)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.8764. Min Act: -0.1700
Data Index: 1418233 (Python Code)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.8764. Min Act: -0.1700
Data Index: 1559321 (Python Code)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4436. Min Range: -3.4436
Max Act: 2.8764. Min Act: -0.1700
Data Index: 1466826 (Python Code)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19