Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.3547. Min Act: -0.1700
Data Index: 2819381 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.3547. Min Act: -0.1700
Data Index: 8630064 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.3860. Min Act: -0.1700
Data Index: 8098924 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.3235. Min Act: -0.1700
Data Index: 3547640 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.2610. Min Act: -0.1700
Data Index: 7729179 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.2922. Min Act: -0.1700
Data Index: 2139523 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.2922. Min Act: -0.1700
Data Index: 5692434 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.2610. Min Act: -0.1700
Data Index: 5428019 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.2922. Min Act: -0.1700
Data Index: 8469011 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.1985. Min Act: -0.1700
Data Index: 7465402 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.2610. Min Act: -0.1700
Data Index: 4340056 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.2297. Min Act: -0.1700
Data Index: 4340057 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.1985. Min Act: -0.1700
Data Index: 992579 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.1985. Min Act: -0.1700
Data Index: 1348351 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.1985. Min Act: -0.1700
Data Index: 5471424 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.1360. Min Act: -0.1700
Data Index: 6303313 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.0735. Min Act: -0.1700
Data Index: 5370507 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.1672. Min Act: -0.1700
Data Index: 2139522 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3860. Min Range: -5.3860
Max Act: 5.1047. Min Act: -0.1700
Data Index: 6642129 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3860. Min Range: -5.3860
Max Act: 4.9797. Min Act: -0.1700
Data Index: 5863100 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19