Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4084 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5576. Min Range: -7.5576
Max Act: 7.5576. Min Act: -0.1700
Data Index: 3308629 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5576. Min Range: -7.5576
Max Act: 7.3701. Min Act: -0.1700
Data Index: 5110609 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5576. Min Range: -7.5576
Max Act: 7.2139. Min Act: -0.1700
Data Index: 6108053 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5576. Min Range: -7.5576
Max Act: 7.2139. Min Act: -0.1700
Data Index: 3739378 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5576. Min Range: -7.5576
Max Act: 7.1514. Min Act: -0.1700
Data Index: 5803474 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5576. Min Range: -7.5576
Max Act: 7.1201. Min Act: -0.1700
Data Index: 499762 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5576. Min Range: -7.5576
Max Act: 7.0889. Min Act: -0.1700
Data Index: 4799383 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5576. Min Range: -7.5576
Max Act: 7.0889. Min Act: -0.1700
Data Index: 4066973 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.9639. Min Act: -0.1700
Data Index: 4376347 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.9326. Min Act: -0.1700
Data Index: 6344729 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.9326. Min Act: -0.1700
Data Index: 5939759 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.9326. Min Act: -0.1700
Data Index: 6737837 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.9326. Min Act: -0.1700
Data Index: 6420760 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.8701. Min Act: -0.1700
Data Index: 5578746 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.8701. Min Act: -0.1700
Data Index: 5346942 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.8701. Min Act: -0.1700
Data Index: 6112332 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.9014. Min Act: -0.1700
Data Index: 519990 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.8701. Min Act: -0.1700
Data Index: 7466143 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.8389. Min Act: -0.1700
Data Index: 5594489 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5576. Min Range: -7.5576
Max Act: 6.8389. Min Act: -0.1700
Data Index: 4359275 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19