Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6362 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.9300. Min Act: -0.1700
Data Index: 120230 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.7425. Min Act: -0.1700
Data Index: 4450661 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.7112. Min Act: -0.1700
Data Index: 3279731 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.6487. Min Act: -0.1700
Data Index: 8429263 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.6175. Min Act: -0.1700
Data Index: 5061780 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.5550. Min Act: -0.1700
Data Index: 3153162 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.5862. Min Act: -0.1700
Data Index: 2067284 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.5862. Min Act: -0.1700
Data Index: 8149344 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.5862. Min Act: -0.1700
Data Index: 8287209 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4925. Min Act: -0.1700
Data Index: 834556 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4925. Min Act: -0.1700
Data Index: 1723549 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4925. Min Act: -0.1700
Data Index: 556160 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4925. Min Act: -0.1700
Data Index: 6907138 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4925. Min Act: -0.1700
Data Index: 1252463 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4925. Min Act: -0.1700
Data Index: 8067161 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4612. Min Act: -0.1700
Data Index: 89396 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4300. Min Act: -0.1700
Data Index: 3100513 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4300. Min Act: -0.1700
Data Index: 948674 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4300. Min Act: -0.1700
Data Index: 955449 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.4300. Min Act: -0.1700
Data Index: 2958903 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19