Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 754 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.5020. Min Act: -0.1700
Data Index: 689944 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.4708. Min Act: -0.1700
Data Index: 5007421 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.4083. Min Act: -0.1700
Data Index: 4426877 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.3770. Min Act: -0.1700
Data Index: 4280266 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.3770. Min Act: -0.1700
Data Index: 8004288 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.2520. Min Act: -0.1700
Data Index: 3109552 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.2208. Min Act: -0.1700
Data Index: 3501425 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.1895. Min Act: -0.1700
Data Index: 689945 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.2208. Min Act: -0.1700
Data Index: 8040955 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.1895. Min Act: -0.1700
Data Index: 4733233 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.1583. Min Act: -0.1700
Data Index: 2246253 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.0958. Min Act: -0.1700
Data Index: 4021671 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.0958. Min Act: -0.1700
Data Index: 592535 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.0958. Min Act: -0.1700
Data Index: 3366119 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.0333. Min Act: -0.1700
Data Index: 912243 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.0333. Min Act: -0.1700
Data Index: 2613246 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.0333. Min Act: -0.1700
Data Index: 31662 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.0333. Min Act: -0.1700
Data Index: 2274877 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.0333. Min Act: -0.1700
Data Index: 3366118 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5020. Min Range: -6.5020
Max Act: 6.0020. Min Act: -0.1700
Data Index: 7472448 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19