Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.6277. Min Act: -0.1700
Data Index: 4604364 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.6277. Min Act: -0.1700
Data Index: 4594945 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.5652. Min Act: -0.1700
Data Index: 1394711 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.5652. Min Act: -0.1700
Data Index: 4538820 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.5027. Min Act: -0.1700
Data Index: 1394707 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.5027. Min Act: -0.1700
Data Index: 1007832 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.4402. Min Act: -0.1700
Data Index: 8679846 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.4402. Min Act: -0.1700
Data Index: 1394708 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.4402. Min Act: -0.1700
Data Index: 5476111 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.4402. Min Act: -0.1700
Data Index: 1176513 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.4402. Min Act: -0.1700
Data Index: 7838522 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.4402. Min Act: -0.1700
Data Index: 4257355 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.4402. Min Act: -0.1700
Data Index: 258586 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.3777. Min Act: -0.1700
Data Index: 4622520 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.3777. Min Act: -0.1700
Data Index: 1007835 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.3777. Min Act: -0.1700
Data Index: 1007836 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.3777. Min Act: -0.1700
Data Index: 5890496 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.3777. Min Act: -0.1700
Data Index: 2068968 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.3777. Min Act: -0.1700
Data Index: 5222307 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6277. Min Range: -7.6277
Max Act: 7.3777. Min Act: -0.1700
Data Index: 4886577 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19