Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4320 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.2429. Min Act: -0.1700
Data Index: 3163358 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.1804. Min Act: -0.1700
Data Index: 6487274 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.1492. Min Act: -0.1700
Data Index: 5430575 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.0867. Min Act: -0.1700
Data Index: 2334015 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.0554. Min Act: -0.1700
Data Index: 1896082 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.0867. Min Act: -0.1700
Data Index: 2417387 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.0554. Min Act: -0.1700
Data Index: 4465363 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.0242. Min Act: -0.1700
Data Index: 1203370 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.0242. Min Act: -0.1700
Data Index: 3527267 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2429. Min Range: -7.2429
Max Act: 7.0242. Min Act: -0.1700
Data Index: 1854159 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.9929. Min Act: -0.1700
Data Index: 8023301 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.9617. Min Act: -0.1700
Data Index: 7720158 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.9304. Min Act: -0.1700
Data Index: 2966019 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.9304. Min Act: -0.1700
Data Index: 7624926 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.8992. Min Act: -0.1700
Data Index: 1761199 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.8992. Min Act: -0.1700
Data Index: 5553006 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.8367. Min Act: -0.1700
Data Index: 1319530 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.8367. Min Act: -0.1700
Data Index: 5450167 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.7742. Min Act: -0.1700
Data Index: 4223022 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2429. Min Range: -7.2429
Max Act: 6.8054. Min Act: -0.1700
Data Index: 4648275 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19