Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2206 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2362. Min Range: -8.2362
Max Act: 8.2362. Min Act: -0.1700
Data Index: 8772138 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2362. Min Range: -8.2362
Max Act: 8.2362. Min Act: -0.1700
Data Index: 2793203 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2362. Min Range: -8.2362
Max Act: 8.1112. Min Act: -0.1700
Data Index: 6826932 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2362. Min Range: -8.2362
Max Act: 8.0175. Min Act: -0.1700
Data Index: 6561023 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2362. Min Range: -8.2362
Max Act: 8.0487. Min Act: -0.1700
Data Index: 1454343 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.9862. Min Act: -0.1700
Data Index: 7412689 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.9862. Min Act: -0.1700
Data Index: 3141305 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.9237. Min Act: -0.1700
Data Index: 2664053 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.9237. Min Act: -0.1700
Data Index: 3088740 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.9237. Min Act: -0.1700
Data Index: 1673554 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.8925. Min Act: -0.1700
Data Index: 1754649 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.8612. Min Act: -0.1700
Data Index: 8322989 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.8612. Min Act: -0.1700
Data Index: 1147533 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.8612. Min Act: -0.1700
Data Index: 6675526 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.7987. Min Act: -0.1700
Data Index: 8789496 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.7987. Min Act: -0.1700
Data Index: 111023 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.7362. Min Act: -0.1700
Data Index: 4699883 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.7675. Min Act: -0.1700
Data Index: 981436 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.7675. Min Act: -0.1700
Data Index: 5003524 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2362. Min Range: -8.2362
Max Act: 7.7675. Min Act: -0.1700
Data Index: 3141306 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19