Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2018 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.6280. Min Act: -0.1700
Data Index: 1374700 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.5654. Min Act: -0.1700
Data Index: 1369801 (Python Code)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.5340. Min Act: -0.1700
Data Index: 1439081 (Python Code)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.5654. Min Act: -0.1700
Data Index: 1577877 (Python Code)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.5340. Min Act: -0.1700
Data Index: 1507569 (Python Code)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.5340. Min Act: -0.1700
Data Index: 1361566 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.5027. Min Act: -0.1700
Data Index: 1365238 (Python Code)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.5027. Min Act: -0.1700
Data Index: 1479009 (Python Code)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4714. Min Act: -0.1700
Data Index: 1541167 (Python Code)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4714. Min Act: -0.1700
Data Index: 1475180 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4714. Min Act: -0.1700
Data Index: 1457200 (Python Code)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4714. Min Act: -0.1700
Data Index: 1466106 (Python Code)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4400. Min Act: -0.1700
Data Index: 1412066 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4400. Min Act: -0.1700
Data Index: 1547148 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4714. Min Act: -0.1700
Data Index: 1581033 (Python Code)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4087. Min Act: -0.1700
Data Index: 1550204 (Python Code)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4243. Min Act: -0.1700
Data Index: 1522766 (Python Code)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4243. Min Act: -0.1700
Data Index: 1421033 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4087. Min Act: -0.1700
Data Index: 1564322 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6280. Min Range: -3.6280
Max Act: 3.4557. Min Act: -0.1700
Data Index: 1416589 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19