Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2327. Min Range: -8.2327
Max Act: 8.2327. Min Act: -0.1700
Data Index: 5337022 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2327. Min Range: -8.2327
Max Act: 8.1077. Min Act: -0.1700
Data Index: 2677866 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2327. Min Range: -8.2327
Max Act: 8.0452. Min Act: -0.1700
Data Index: 6986882 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2327. Min Range: -8.2327
Max Act: 8.0452. Min Act: -0.1700
Data Index: 6088068 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2327. Min Range: -8.2327
Max Act: 8.0452. Min Act: -0.1700
Data Index: 6788832 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.9827. Min Act: -0.1700
Data Index: 3406290 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.9202. Min Act: -0.1700
Data Index: 6937246 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.8890. Min Act: -0.1700
Data Index: 3302551 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.8577. Min Act: -0.1700
Data Index: 6717522 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.8577. Min Act: -0.1700
Data Index: 6986897 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.8265. Min Act: -0.1700
Data Index: 7618922 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.8265. Min Act: -0.1700
Data Index: 3090888 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.7952. Min Act: -0.1700
Data Index: 5985430 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.7952. Min Act: -0.1700
Data Index: 30281 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.8265. Min Act: -0.1700
Data Index: 8198014 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.7952. Min Act: -0.1700
Data Index: 6717539 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.7952. Min Act: -0.1700
Data Index: 6937253 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.7327. Min Act: -0.1700
Data Index: 570885 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.7327. Min Act: -0.1700
Data Index: 7305157 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2327. Min Range: -8.2327
Max Act: 7.7015. Min Act: -0.1700
Data Index: 6717523 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19