Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5320 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3483. Min Range: -6.3483
Max Act: 6.3483. Min Act: -0.1700
Data Index: 2512016 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3483. Min Range: -6.3483
Max Act: 6.2233. Min Act: -0.1700
Data Index: 1873710 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3483. Min Range: -6.3483
Max Act: 6.2233. Min Act: -0.1700
Data Index: 2568393 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3483. Min Range: -6.3483
Max Act: 6.2233. Min Act: -0.1700
Data Index: 3044264 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3483. Min Range: -6.3483
Max Act: 6.0983. Min Act: -0.1700
Data Index: 7909473 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3483. Min Range: -6.3483
Max Act: 6.0671. Min Act: -0.1700
Data Index: 6099468 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.9421. Min Act: -0.1700
Data Index: 727183 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8796. Min Act: -0.1700
Data Index: 6190177 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.9108. Min Act: -0.1700
Data Index: 3954504 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8796. Min Act: -0.1700
Data Index: 2555119 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8483. Min Act: -0.1700
Data Index: 6655029 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8483. Min Act: -0.1700
Data Index: 8632010 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8483. Min Act: -0.1700
Data Index: 4058144 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8171. Min Act: -0.1700
Data Index: 1662124 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8483. Min Act: -0.1700
Data Index: 8555514 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8483. Min Act: -0.1700
Data Index: 1801952 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8171. Min Act: -0.1700
Data Index: 6707242 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8171. Min Act: -0.1700
Data Index: 7557282 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8171. Min Act: -0.1700
Data Index: 6682154 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3483. Min Range: -6.3483
Max Act: 5.8171. Min Act: -0.1700
Data Index: 6992467 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19