Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 36 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0201. Min Range: -3.0201
Max Act: 3.0201. Min Act: -0.1700
Data Index: 408534 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.5092. Min Act: -0.1700
Data Index: 836727 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.5092. Min Act: -0.1700
Data Index: 1176117 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.4443. Min Act: -0.1700
Data Index: 566144 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.4117. Min Act: -0.1700
Data Index: 1206780 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3954. Min Act: -0.1700
Data Index: 547284 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3954. Min Act: -0.1700
Data Index: 103259 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3954. Min Act: -0.1700
Data Index: 81940 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.4117. Min Act: -0.1700
Data Index: 1159348 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3791. Min Act: -0.1700
Data Index: 1393349 (Python Code)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3791. Min Act: -0.1700
Data Index: 1248237 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3954. Min Act: -0.1700
Data Index: 1014206 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3628. Min Act: -0.1700
Data Index: 1208138 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3628. Min Act: -0.1700
Data Index: 395805 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3300. Min Act: -0.1700
Data Index: 438790 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3300. Min Act: -0.1700
Data Index: 79247 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3464. Min Act: -0.1700
Data Index: 1037963 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3136. Min Act: -0.1700
Data Index: 819088 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3300. Min Act: -0.1700
Data Index: 753745 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0201. Min Range: -3.0201
Max Act: 2.3300. Min Act: -0.1700
Data Index: 76417 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19