Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1444. Min Range: -8.1444
Max Act: 8.1444. Min Act: -0.1700
Data Index: 8467414 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.5819. Min Act: -0.1700
Data Index: 3037012 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.5194. Min Act: -0.1700
Data Index: 6149295 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.4257. Min Act: -0.1700
Data Index: 2710058 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.4569. Min Act: -0.1700
Data Index: 7406943 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.4569. Min Act: -0.1700
Data Index: 1437604 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.4257. Min Act: -0.1700
Data Index: 4140204 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3632. Min Act: -0.1700
Data Index: 3471585 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3944. Min Act: -0.1700
Data Index: 3472308 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3632. Min Act: -0.1700
Data Index: 4951867 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3319. Min Act: -0.1700
Data Index: 5607685 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3319. Min Act: -0.1700
Data Index: 4561455 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3632. Min Act: -0.1700
Data Index: 199294 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3007. Min Act: -0.1700
Data Index: 2477277 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3007. Min Act: -0.1700
Data Index: 3519961 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.2694. Min Act: -0.1700
Data Index: 4047972 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3319. Min Act: -0.1700
Data Index: 1653502 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.3007. Min Act: -0.1700
Data Index: 2428085 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.2069. Min Act: -0.1700
Data Index: 7293513 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1444. Min Range: -8.1444
Max Act: 7.2382. Min Act: -0.1700
Data Index: 8451035 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19