Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4424. Min Range: -6.4424
Max Act: 6.4424. Min Act: -0.1700
Data Index: 7747718 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4424. Min Range: -6.4424
Max Act: 6.2549. Min Act: -0.1700
Data Index: 7301579 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4424. Min Range: -6.4424
Max Act: 6.0361. Min Act: -0.1700
Data Index: 6479956 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4424. Min Range: -6.4424
Max Act: 6.0361. Min Act: -0.1700
Data Index: 5880158 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.9736. Min Act: -0.1700
Data Index: 2354339 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.9736. Min Act: -0.1700
Data Index: 6592765 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.9111. Min Act: -0.1700
Data Index: 4983754 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.9424. Min Act: -0.1700
Data Index: 2007006 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.9111. Min Act: -0.1700
Data Index: 8123431 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.8486. Min Act: -0.1700
Data Index: 862236 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.8486. Min Act: -0.1700
Data Index: 3761945 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.8174. Min Act: -0.1700
Data Index: 5999923 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.8486. Min Act: -0.1700
Data Index: 3817062 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.7861. Min Act: -0.1700
Data Index: 4487424 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.7861. Min Act: -0.1700
Data Index: 4204786 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.7861. Min Act: -0.1700
Data Index: 2685421 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.7861. Min Act: -0.1700
Data Index: 4131543 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.8174. Min Act: -0.1700
Data Index: 1850640 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.7861. Min Act: -0.1700
Data Index: 8038230 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4424. Min Range: -6.4424
Max Act: 5.7861. Min Act: -0.1700
Data Index: 4119321 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19