Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5992 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3595. Min Range: -7.3595
Max Act: 7.3595. Min Act: -0.1700
Data Index: 530498 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.9220. Min Act: -0.1700
Data Index: 1410384 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.9220. Min Act: -0.1700
Data Index: 4907875 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.9220. Min Act: -0.1700
Data Index: 6674837 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.8907. Min Act: -0.1700
Data Index: 7190994 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.8595. Min Act: -0.1700
Data Index: 6384151 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.8282. Min Act: -0.1700
Data Index: 5740598 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.7657. Min Act: -0.1700
Data Index: 6451740 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.7345. Min Act: -0.1700
Data Index: 6863811 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.7345. Min Act: -0.1700
Data Index: 7032894 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.7032. Min Act: -0.1700
Data Index: 3103711 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.6720. Min Act: -0.1700
Data Index: 3381963 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.6407. Min Act: -0.1700
Data Index: 2957538 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.6407. Min Act: -0.1700
Data Index: 4499045 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.6407. Min Act: -0.1700
Data Index: 432231 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.6407. Min Act: -0.1700
Data Index: 6637052 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.6095. Min Act: -0.1700
Data Index: 5449768 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.5470. Min Act: -0.1700
Data Index: 3392354 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.5782. Min Act: -0.1700
Data Index: 3616368 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3595. Min Range: -7.3595
Max Act: 6.6095. Min Act: -0.1700
Data Index: 568704 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19