Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3228. Min Range: -8.3228
Max Act: 8.3228. Min Act: -0.1700
Data Index: 6235826 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3228. Min Range: -8.3228
Max Act: 8.2603. Min Act: -0.1700
Data Index: 8513254 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3228. Min Range: -8.3228
Max Act: 8.1978. Min Act: -0.1700
Data Index: 5541625 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3228. Min Range: -8.3228
Max Act: 8.0728. Min Act: -0.1700
Data Index: 8303804 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.9478. Min Act: -0.1700
Data Index: 3634901 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.9478. Min Act: -0.1700
Data Index: 5212550 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.8853. Min Act: -0.1698
Data Index: 6105252 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.8228. Min Act: -0.1700
Data Index: 4306342 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.8853. Min Act: -0.1700
Data Index: 4209560 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.8228. Min Act: -0.1700
Data Index: 7534238 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.8228. Min Act: -0.1700
Data Index: 24859 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.7603. Min Act: -0.1700
Data Index: 3068533 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.7603. Min Act: -0.1700
Data Index: 7436856 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.6978. Min Act: -0.1700
Data Index: 939558 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.6978. Min Act: -0.1700
Data Index: 352485 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.6353. Min Act: -0.1700
Data Index: 449728 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.7603. Min Act: -0.1700
Data Index: 2400524 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.6353. Min Act: -0.1700
Data Index: 3249028 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.6353. Min Act: -0.1700
Data Index: 3892446 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3228. Min Range: -8.3228
Max Act: 7.6353. Min Act: -0.1700
Data Index: 3141104 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19