Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3391 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.5712. Min Act: -0.1700
Data Index: 8074958 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.3832. Min Act: -0.1700
Data Index: 3216322 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.2576. Min Act: -0.1700
Data Index: 4872445 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.2262. Min Act: -0.1700
Data Index: 2223376 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.2105. Min Act: -0.1700
Data Index: 4254221 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1475. Min Act: -0.1700
Data Index: 6922854 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1633. Min Act: -0.1700
Data Index: 8283017 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1475. Min Act: -0.1700
Data Index: 3266869 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1318. Min Act: -0.1700
Data Index: 7832042 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1318. Min Act: -0.1700
Data Index: 4549074 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1318. Min Act: -0.1700
Data Index: 2304305 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1161. Min Act: -0.1700
Data Index: 2616262 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1003. Min Act: -0.1700
Data Index: 1312268 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1003. Min Act: -0.1700
Data Index: 1962546 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.1003. Min Act: -0.1700
Data Index: 4331008 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.0845. Min Act: -0.1700
Data Index: 4100323 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.0845. Min Act: -0.1700
Data Index: 4356600 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.0688. Min Act: -0.1700
Data Index: 7064576 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.0530. Min Act: -0.1700
Data Index: 3864134 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5712. Min Range: -3.5712
Max Act: 3.0688. Min Act: -0.1700
Data Index: 7427300 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19