Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1427. Min Range: -7.1427
Max Act: 7.1427. Min Act: -0.1700
Data Index: 5708882 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.8302. Min Act: -0.1700
Data Index: 5836876 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.7677. Min Act: -0.1700
Data Index: 4434210 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.7364. Min Act: -0.1700
Data Index: 5682124 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.7364. Min Act: -0.1700
Data Index: 2507398 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.6739. Min Act: -0.1700
Data Index: 1866651 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.6427. Min Act: -0.1700
Data Index: 5822317 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.5489. Min Act: -0.1700
Data Index: 5806511 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.5177. Min Act: -0.1700
Data Index: 1215572 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.5177. Min Act: -0.1700
Data Index: 7427433 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.4864. Min Act: -0.1700
Data Index: 4629920 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.4552. Min Act: -0.1700
Data Index: 6373715 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.4552. Min Act: -0.1700
Data Index: 1529682 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.4552. Min Act: -0.1700
Data Index: 6826279 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.4239. Min Act: -0.1700
Data Index: 5909179 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.4239. Min Act: -0.1700
Data Index: 6504565 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.4239. Min Act: -0.1700
Data Index: 6559065 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.4239. Min Act: -0.1700
Data Index: 8704570 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.4239. Min Act: -0.1700
Data Index: 2206789 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1427. Min Range: -7.1427
Max Act: 6.3927. Min Act: -0.1700
Data Index: 7444412 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19