Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.3304. Min Act: -0.1700
Data Index: 6962506 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2991. Min Act: -0.1700
Data Index: 6747844 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2991. Min Act: -0.1700
Data Index: 3912546 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2054. Min Act: -0.1700
Data Index: 58432 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2054. Min Act: -0.1700
Data Index: 8362959 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2054. Min Act: -0.1700
Data Index: 2004692 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.2054. Min Act: -0.1700
Data Index: 5920371 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1429. Min Act: -0.1700
Data Index: 4048607 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.1429. Min Act: -0.1700
Data Index: 1510521 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.0491. Min Act: -0.1700
Data Index: 3168679 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.0491. Min Act: -0.1700
Data Index: 8536554 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.0491. Min Act: -0.1700
Data Index: 7695639 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.0179. Min Act: -0.1700
Data Index: 3628478 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3304. Min Range: -5.3304
Max Act: 4.9866. Min Act: -0.1700
Data Index: 4149537 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3304. Min Range: -5.3304
Max Act: 5.0179. Min Act: -0.1700
Data Index: 8173111 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3304. Min Range: -5.3304
Max Act: 4.9554. Min Act: -0.1700
Data Index: 3260429 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3304. Min Range: -5.3304
Max Act: 4.9554. Min Act: -0.1700
Data Index: 107832 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3304. Min Range: -5.3304
Max Act: 4.8929. Min Act: -0.1700
Data Index: 6041492 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3304. Min Range: -5.3304
Max Act: 4.9241. Min Act: -0.1700
Data Index: 6142863 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3304. Min Range: -5.3304
Max Act: 4.9241. Min Act: -0.1700
Data Index: 4551992 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19