Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3765 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1502. Min Range: -7.1502
Max Act: 7.1502. Min Act: -0.1700
Data Index: 6264665 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1502. Min Range: -7.1502
Max Act: 6.6502. Min Act: -0.1700
Data Index: 8551026 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1502. Min Range: -7.1502
Max Act: 6.3065. Min Act: -0.1700
Data Index: 4611852 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1502. Min Range: -7.1502
Max Act: 6.2440. Min Act: -0.1700
Data Index: 4827825 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1502. Min Range: -7.1502
Max Act: 6.1815. Min Act: -0.1700
Data Index: 7187527 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1502. Min Range: -7.1502
Max Act: 6.0877. Min Act: -0.1700
Data Index: 4611853 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1502. Min Range: -7.1502
Max Act: 6.0565. Min Act: -0.1700
Data Index: 1166405 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1502. Min Range: -7.1502
Max Act: 6.0565. Min Act: -0.1700
Data Index: 6384807 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1502. Min Range: -7.1502
Max Act: 6.0252. Min Act: -0.1700
Data Index: 6202902 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9627. Min Act: -0.1700
Data Index: 4914612 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9315. Min Act: -0.1700
Data Index: 7556842 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9627. Min Act: -0.1700
Data Index: 4173023 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9627. Min Act: -0.1700
Data Index: 3776091 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9940. Min Act: -0.1700
Data Index: 2139326 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9315. Min Act: -0.1700
Data Index: 1446367 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9315. Min Act: -0.1700
Data Index: 6764113 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9002. Min Act: -0.1700
Data Index: 3598293 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9002. Min Act: -0.1700
Data Index: 774302 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9002. Min Act: -0.1700
Data Index: 5825985 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1502. Min Range: -7.1502
Max Act: 5.9002. Min Act: -0.1700
Data Index: 4159253 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19