Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7225. Min Range: -7.7225
Max Act: 7.7225. Min Act: -0.1700
Data Index: 1371851 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.9412. Min Act: -0.1700
Data Index: 4921058 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.8787. Min Act: -0.1700
Data Index: 6068232 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.8162. Min Act: -0.1700
Data Index: 5726624 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.6912. Min Act: -0.1700
Data Index: 7915096 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.6912. Min Act: -0.1700
Data Index: 7285361 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.6600. Min Act: -0.1700
Data Index: 6299477 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.5975. Min Act: -0.1700
Data Index: 2935438 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.5975. Min Act: -0.1700
Data Index: 1944086 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.5662. Min Act: -0.1700
Data Index: 5429832 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.5662. Min Act: -0.1700
Data Index: 4678079 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.5350. Min Act: -0.1700
Data Index: 2635861 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.5037. Min Act: -0.1700
Data Index: 8605129 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.5037. Min Act: -0.1700
Data Index: 3434316 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.4725. Min Act: -0.1700
Data Index: 7845253 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.4412. Min Act: -0.1700
Data Index: 7297069 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.4412. Min Act: -0.1700
Data Index: 4162324 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.4100. Min Act: -0.1700
Data Index: 4084923 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.4100. Min Act: -0.1700
Data Index: 7354608 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7225. Min Range: -7.7225
Max Act: 6.4100. Min Act: -0.1700
Data Index: 5359840 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19