Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1126 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7316. Min Range: -6.7316
Max Act: 6.7316. Min Act: -0.1700
Data Index: 51795 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7316. Min Range: -6.7316
Max Act: 6.7003. Min Act: -0.1700
Data Index: 4483070 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7316. Min Range: -6.7316
Max Act: 6.3566. Min Act: -0.1700
Data Index: 8360820 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7316. Min Range: -6.7316
Max Act: 6.3566. Min Act: -0.1700
Data Index: 3564734 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7316. Min Range: -6.7316
Max Act: 6.1691. Min Act: -0.1700
Data Index: 2697092 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7316. Min Range: -6.7316
Max Act: 6.1378. Min Act: -0.1700
Data Index: 4528968 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7316. Min Range: -6.7316
Max Act: 6.0441. Min Act: -0.1700
Data Index: 2104985 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7316. Min Range: -6.7316
Max Act: 6.0441. Min Act: -0.1700
Data Index: 6811617 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.9816. Min Act: -0.1700
Data Index: 3424661 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.9191. Min Act: -0.1700
Data Index: 8799208 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.8878. Min Act: -0.1700
Data Index: 1288485 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.9191. Min Act: -0.1700
Data Index: 4182154 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.8566. Min Act: -0.1700
Data Index: 4137964 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.8253. Min Act: -0.1700
Data Index: 8815049 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.8566. Min Act: -0.1700
Data Index: 5211576 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.8253. Min Act: -0.1700
Data Index: 7452870 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.7941. Min Act: -0.1700
Data Index: 958103 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.7941. Min Act: -0.1700
Data Index: 1511804 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.8253. Min Act: -0.1700
Data Index: 3486043 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7316. Min Range: -6.7316
Max Act: 5.7941. Min Act: -0.1700
Data Index: 4240018 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19