Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.5982. Min Act: -0.1700
Data Index: 4334050 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.4420. Min Act: -0.1700
Data Index: 6495414 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.2545. Min Act: -0.1700
Data Index: 4422546 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.1920. Min Act: -0.1700
Data Index: 2833165 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.1295. Min Act: -0.1700
Data Index: 4816640 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.0670. Min Act: -0.1700
Data Index: 7667025 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.0045. Min Act: -0.1700
Data Index: 3797256 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5982. Min Range: -5.5982
Max Act: 5.0045. Min Act: -0.1700
Data Index: 5742828 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.9420. Min Act: -0.1700
Data Index: 6355264 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.8795. Min Act: -0.1700
Data Index: 2400538 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.8795. Min Act: -0.1700
Data Index: 5491669 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.8482. Min Act: -0.1700
Data Index: 7921572 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.8482. Min Act: -0.1700
Data Index: 6365779 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.8482. Min Act: -0.1700
Data Index: 7703950 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.8482. Min Act: -0.1700
Data Index: 5738923 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.8170. Min Act: -0.1700
Data Index: 3536633 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.7857. Min Act: -0.1700
Data Index: 1401450 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.7857. Min Act: -0.1700
Data Index: 1286743 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.7857. Min Act: -0.1700
Data Index: 7912740 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5982. Min Range: -5.5982
Max Act: 4.7545. Min Act: -0.1700
Data Index: 3867842 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19