Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.7783. Min Act: -0.1700
Data Index: 1943968 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.6220. Min Act: -0.1700
Data Index: 7668387 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.5595. Min Act: -0.1700
Data Index: 2516146 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.5283. Min Act: -0.1700
Data Index: 8058549 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.4345. Min Act: -0.1700
Data Index: 5496599 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.3720. Min Act: -0.1700
Data Index: 2179251 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.3720. Min Act: -0.1700
Data Index: 6306921 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.3720. Min Act: -0.1700
Data Index: 3587500 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.3408. Min Act: -0.1700
Data Index: 4447230 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.3408. Min Act: -0.1700
Data Index: 5520245 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.2783. Min Act: -0.1700
Data Index: 8740135 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.2783. Min Act: -0.1700
Data Index: 5237392 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.2470. Min Act: -0.1700
Data Index: 7026357 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.2158. Min Act: -0.1700
Data Index: 5374684 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.2158. Min Act: -0.1700
Data Index: 4389501 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.2158. Min Act: -0.1700
Data Index: 4143439 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.1845. Min Act: -0.1700
Data Index: 8001935 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.1533. Min Act: -0.1700
Data Index: 1320260 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.1220. Min Act: -0.1700
Data Index: 8374485 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7783. Min Range: -7.7783
Max Act: 7.1533. Min Act: -0.1700
Data Index: 4337164 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19