Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2432 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2448. Min Range: -4.2448
Max Act: 4.2448. Min Act: -0.1700
Data Index: 7133545 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2448. Min Range: -4.2448
Max Act: 4.1510. Min Act: -0.1700
Data Index: 5875751 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2448. Min Range: -4.2448
Max Act: 4.0260. Min Act: -0.1700
Data Index: 1102537 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2448. Min Range: -4.2448
Max Act: 4.0260. Min Act: -0.1700
Data Index: 224574 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9635. Min Act: -0.1700
Data Index: 7720414 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9947. Min Act: -0.1700
Data Index: 1231186 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9635. Min Act: -0.1700
Data Index: 7300184 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9322. Min Act: -0.1700
Data Index: 7997220 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9322. Min Act: -0.1700
Data Index: 6399511 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9322. Min Act: -0.1700
Data Index: 8492584 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9322. Min Act: -0.1700
Data Index: 356432 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9009. Min Act: -0.1700
Data Index: 2357935 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9009. Min Act: -0.1700
Data Index: 7997218 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.9009. Min Act: -0.1700
Data Index: 1689550 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.8697. Min Act: -0.1700
Data Index: 6476361 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.8697. Min Act: -0.1700
Data Index: 2010324 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.8697. Min Act: -0.1700
Data Index: 4314690 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.8697. Min Act: -0.1700
Data Index: 1159051 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.8384. Min Act: -0.1700
Data Index: 1435919 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2448. Min Range: -4.2448
Max Act: 3.8384. Min Act: -0.1700
Data Index: 2062916 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19