Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1013 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.8888. Min Act: -0.1700
Data Index: 1515140 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.8253. Min Act: -0.1700
Data Index: 697565 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.8094. Min Act: -0.1700
Data Index: 367747 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.8253. Min Act: -0.1700
Data Index: 351461 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.8094. Min Act: -0.1700
Data Index: 938920 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.8094. Min Act: -0.1700
Data Index: 611136 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7934. Min Act: -0.1700
Data Index: 1399732 (Python Code)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7934. Min Act: -0.1700
Data Index: 633416 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7934. Min Act: -0.1700
Data Index: 168622 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7934. Min Act: -0.1700
Data Index: 1309021 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7616. Min Act: -0.1700
Data Index: 105948 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7616. Min Act: -0.1700
Data Index: 958711 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7775. Min Act: -0.1700
Data Index: 353203 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7775. Min Act: -0.1700
Data Index: 179640 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7775. Min Act: -0.1700
Data Index: 721511 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7456. Min Act: -0.1700
Data Index: 985672 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7456. Min Act: -0.1700
Data Index: 1176992 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7775. Min Act: -0.1700
Data Index: 58210 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7296. Min Act: -0.1700
Data Index: 915086 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8888. Min Range: -2.8888
Max Act: 2.7456. Min Act: -0.1700
Data Index: 482724 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19