Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.6699. Min Act: -0.1700
Data Index: 754074 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.6699. Min Act: -0.1700
Data Index: 6127903 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.6074. Min Act: -0.1700
Data Index: 6003433 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.6074. Min Act: -0.1700
Data Index: 3374481 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.4824. Min Act: -0.1700
Data Index: 4436960 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.4824. Min Act: -0.1700
Data Index: 6243444 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.4199. Min Act: -0.1700
Data Index: 465685 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.4199. Min Act: -0.1700
Data Index: 4028900 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.3574. Min Act: -0.1700
Data Index: 5035841 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.3574. Min Act: -0.1700
Data Index: 6102713 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.2949. Min Act: -0.1700
Data Index: 6116490 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.2949. Min Act: -0.1700
Data Index: 5817894 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.2324. Min Act: -0.1700
Data Index: 835134 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.1699. Min Act: -0.1700
Data Index: 8463508 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.1699. Min Act: -0.1700
Data Index: 3076527 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.2324. Min Act: -0.1700
Data Index: 2790243 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.1699. Min Act: -0.1700
Data Index: 2001926 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.1074. Min Act: -0.1700
Data Index: 2813906 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.1074. Min Act: -0.1700
Data Index: 4356320 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.6699. Min Range: -13.6699
Max Act: 13.1074. Min Act: -0.1700
Data Index: 3589772 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19