Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.8845. Min Act: -0.1700
Data Index: 6875877 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.8845. Min Act: -0.1700
Data Index: 3235788 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.7595. Min Act: -0.1700
Data Index: 5505896 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.6970. Min Act: -0.1700
Data Index: 5188730 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.6970. Min Act: -0.1700
Data Index: 3336172 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.6970. Min Act: -0.1700
Data Index: 7473686 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.6970. Min Act: -0.1700
Data Index: 2269431 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.6345. Min Act: -0.1700
Data Index: 237294 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.6033. Min Act: -0.1700
Data Index: 3639439 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.5095. Min Act: -0.1700
Data Index: 4293385 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.4783. Min Act: -0.1700
Data Index: 2646770 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.4783. Min Act: -0.1700
Data Index: 903020 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.4783. Min Act: -0.1700
Data Index: 3544695 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.4783. Min Act: -0.1700
Data Index: 8120489 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.4783. Min Act: -0.1700
Data Index: 1032970 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.4470. Min Act: -0.1700
Data Index: 6271968 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.3845. Min Act: -0.1700
Data Index: 611410 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.3533. Min Act: -0.1700
Data Index: 635078 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.3220. Min Act: -0.1700
Data Index: 4038719 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8845. Min Range: -8.8845
Max Act: 8.3533. Min Act: -0.1700
Data Index: 2412940 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19