Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 391 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.6699. Min Act: -0.1700
Data Index: 3373653 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.6386. Min Act: -0.1700
Data Index: 7886099 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.5761. Min Act: -0.1700
Data Index: 1248562 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.5449. Min Act: -0.1700
Data Index: 6991195 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.5449. Min Act: -0.1700
Data Index: 831093 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.5449. Min Act: -0.1700
Data Index: 4129613 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.5136. Min Act: -0.1700
Data Index: 5697327 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.5136. Min Act: -0.1700
Data Index: 4125345 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.4824. Min Act: -0.1700
Data Index: 6296862 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.4511. Min Act: -0.1700
Data Index: 7165978 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.4199. Min Act: -0.1700
Data Index: 1697457 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.4199. Min Act: -0.1700
Data Index: 1357675 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3886. Min Act: -0.1700
Data Index: 5696022 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3574. Min Act: -0.1700
Data Index: 2542717 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3574. Min Act: -0.1700
Data Index: 4881307 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3886. Min Act: -0.1700
Data Index: 1494501 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.4199. Min Act: -0.1700
Data Index: 3389660 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3574. Min Act: -0.1700
Data Index: 4564684 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.4199. Min Act: -0.1700
Data Index: 302916 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3886. Min Act: -0.1700
Data Index: 3445348 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19