Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 69 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.3109. Min Act: -0.1700
Data Index: 1106591 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.3109. Min Act: -0.1700
Data Index: 509262 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2944. Min Act: -0.1700
Data Index: 1567485 (Python Code)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2780. Min Act: -0.1700
Data Index: 1514169 (Python Code)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2450. Min Act: -0.1700
Data Index: 1216918 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2450. Min Act: -0.1700
Data Index: 1547225 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2615. Min Act: -0.1700
Data Index: 671520 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2450. Min Act: -0.1700
Data Index: 1488265 (Python Code)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2450. Min Act: -0.1700
Data Index: 1566241 (Python Code)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2284. Min Act: -0.1700
Data Index: 1395442 (Python Code)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2119. Min Act: -0.1700
Data Index: 909309 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2119. Min Act: -0.1700
Data Index: 1378146 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2119. Min Act: -0.1700
Data Index: 884078 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2119. Min Act: -0.1700
Data Index: 239865 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.1953. Min Act: -0.1700
Data Index: 1473069 (Python Code)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.1953. Min Act: -0.1700
Data Index: 1362210 (Python Code)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.1953. Min Act: -0.1700
Data Index: 1495281 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.1787. Min Act: -0.1700
Data Index: 1014285 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.2119. Min Act: -0.1700
Data Index: 33396 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3109. Min Range: -2.3109
Max Act: 2.1953. Min Act: -0.1700
Data Index: 630552 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19