Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6039 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2615. Min Range: -7.2615
Max Act: 7.2615. Min Act: -0.1700
Data Index: 5404997 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2615. Min Range: -7.2615
Max Act: 7.2615. Min Act: -0.1700
Data Index: 7097651 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2615. Min Range: -7.2615
Max Act: 7.1990. Min Act: -0.1700
Data Index: 1413038 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2615. Min Range: -7.2615
Max Act: 7.0740. Min Act: -0.1700
Data Index: 2683624 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2615. Min Range: -7.2615
Max Act: 7.0428. Min Act: -0.1700
Data Index: 8453460 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2615. Min Range: -7.2615
Max Act: 7.0740. Min Act: -0.1700
Data Index: 7034867 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.9490. Min Act: -0.1700
Data Index: 5571194 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.9178. Min Act: -0.1700
Data Index: 8792519 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.8865. Min Act: -0.1700
Data Index: 7283462 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.8865. Min Act: -0.1700
Data Index: 2140883 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.8553. Min Act: -0.1700
Data Index: 8254416 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.8553. Min Act: -0.1700
Data Index: 5729498 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.8553. Min Act: -0.1700
Data Index: 995918 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.7928. Min Act: -0.1700
Data Index: 2802203 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.7615. Min Act: -0.1700
Data Index: 4951667 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.7615. Min Act: -0.1700
Data Index: 543547 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.7615. Min Act: -0.1700
Data Index: 2108876 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.7615. Min Act: -0.1700
Data Index: 2784458 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.7303. Min Act: -0.1700
Data Index: 5227760 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2615. Min Range: -7.2615
Max Act: 6.7303. Min Act: -0.1700
Data Index: 4360423 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19