Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 713 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.4951. Min Act: -0.1700
Data Index: 6878733 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.4014. Min Act: -0.1700
Data Index: 214390 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.3389. Min Act: -0.1700
Data Index: 3974773 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.2451. Min Act: -0.1700
Data Index: 44100 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.2139. Min Act: -0.1700
Data Index: 601538 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.1826. Min Act: -0.1700
Data Index: 5882344 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.2139. Min Act: -0.1700
Data Index: 3407607 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.1826. Min Act: -0.1700
Data Index: 204246 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.1826. Min Act: -0.1700
Data Index: 8659667 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.1514. Min Act: -0.1700
Data Index: 8205837 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.1514. Min Act: -0.1700
Data Index: 5295387 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.1201. Min Act: -0.1700
Data Index: 3225023 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.1201. Min Act: -0.1700
Data Index: 7655302 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.1201. Min Act: -0.1700
Data Index: 288286 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.0889. Min Act: -0.1700
Data Index: 5682244 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.0889. Min Act: -0.1700
Data Index: 2806385 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.0889. Min Act: -0.1700
Data Index: 456562 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.0889. Min Act: -0.1700
Data Index: 4597375 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.0576. Min Act: -0.1700
Data Index: 8154034 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4951. Min Range: -4.4951
Max Act: 4.0576. Min Act: -0.1700
Data Index: 642778 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19