Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2553 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.8010. Min Act: -0.1700
Data Index: 984719 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.7385. Min Act: -0.1700
Data Index: 4522108 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.7385. Min Act: -0.1700
Data Index: 6726924 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.5510. Min Act: -0.1700
Data Index: 4756155 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.4885. Min Act: -0.1700
Data Index: 2865865 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.4260. Min Act: -0.1700
Data Index: 1183583 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.4885. Min Act: -0.1700
Data Index: 2653187 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.3635. Min Act: -0.1700
Data Index: 6093321 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.3010. Min Act: -0.1700
Data Index: 4354408 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.3010. Min Act: -0.1700
Data Index: 6383426 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.3010. Min Act: -0.1700
Data Index: 2092703 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.1760. Min Act: -0.1700
Data Index: 1948605 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.1760. Min Act: -0.1700
Data Index: 1658077 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.1760. Min Act: -0.1700
Data Index: 5997521 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.1760. Min Act: -0.1700
Data Index: 3592437 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.1760. Min Act: -0.1700
Data Index: 5169746 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.2385. Min Act: -0.1700
Data Index: 4908984 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.0510. Min Act: -0.1700
Data Index: 7227566 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.0510. Min Act: -0.1700
Data Index: 5418763 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8010. Min Range: -11.8010
Max Act: 11.0510. Min Act: -0.1700
Data Index: 1223586 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19