Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 690 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.2047. Min Act: -0.1700
Data Index: 6963367 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.1735. Min Act: -0.1700
Data Index: 7233560 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.1422. Min Act: -0.1700
Data Index: 4619605 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.1110. Min Act: -0.1700
Data Index: 1111178 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.1110. Min Act: -0.1700
Data Index: 3711462 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.0797. Min Act: -0.1700
Data Index: 5679019 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.0485. Min Act: -0.1700
Data Index: 6450561 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.0172. Min Act: -0.1700
Data Index: 671473 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.0485. Min Act: -0.1700
Data Index: 4589987 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.0172. Min Act: -0.1700
Data Index: 3740244 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2047. Min Range: -5.2047
Max Act: 5.0172. Min Act: -0.1700
Data Index: 1133754 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2047. Min Range: -5.2047
Max Act: 4.9860. Min Act: -0.1700
Data Index: 4537429 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2047. Min Range: -5.2047
Max Act: 4.9860. Min Act: -0.1700
Data Index: 3701823 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2047. Min Range: -5.2047
Max Act: 4.9547. Min Act: -0.1700
Data Index: 6169272 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2047. Min Range: -5.2047
Max Act: 4.9547. Min Act: -0.1700
Data Index: 1105175 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2047. Min Range: -5.2047
Max Act: 4.9547. Min Act: -0.1700
Data Index: 7086365 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2047. Min Range: -5.2047
Max Act: 4.9235. Min Act: -0.1700
Data Index: 2316628 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2047. Min Range: -5.2047
Max Act: 4.9235. Min Act: -0.1700
Data Index: 6077475 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2047. Min Range: -5.2047
Max Act: 4.9235. Min Act: -0.1700
Data Index: 2685290 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2047. Min Range: -5.2047
Max Act: 4.9235. Min Act: -0.1700
Data Index: 3204284 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19