Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 438 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0110. Min Range: -5.0110
Max Act: 5.0110. Min Act: -0.1700
Data Index: 1708885 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.8235. Min Act: -0.1700
Data Index: 8123913 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.6672. Min Act: -0.1700
Data Index: 6489805 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.6047. Min Act: -0.1700
Data Index: 8393626 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.6047. Min Act: -0.1700
Data Index: 3940530 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.5735. Min Act: -0.1700
Data Index: 4291328 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.5735. Min Act: -0.1700
Data Index: 7624892 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.5422. Min Act: -0.1700
Data Index: 5844644 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.5110. Min Act: -0.1700
Data Index: 8491692 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.5110. Min Act: -0.1700
Data Index: 4048625 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.5110. Min Act: -0.1700
Data Index: 8275315 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.5110. Min Act: -0.1700
Data Index: 8154235 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4797. Min Act: -0.1700
Data Index: 5234070 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4797. Min Act: -0.1700
Data Index: 8737659 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4485. Min Act: -0.1700
Data Index: 1579354 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4485. Min Act: -0.1700
Data Index: 1577141 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4485. Min Act: -0.1700
Data Index: 4922070 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4485. Min Act: -0.1700
Data Index: 895837 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4172. Min Act: -0.1700
Data Index: 3293183 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0110. Min Range: -5.0110
Max Act: 4.4172. Min Act: -0.1700
Data Index: 3123308 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19