Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0904. Min Range: -7.0904
Max Act: 7.0904. Min Act: -0.1700
Data Index: 8652172 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.9342. Min Act: -0.1700
Data Index: 5356246 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.8404. Min Act: -0.1700
Data Index: 5408770 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.7779. Min Act: -0.1700
Data Index: 8719685 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.7779. Min Act: -0.1700
Data Index: 4077697 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.7779. Min Act: -0.1700
Data Index: 3520399 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.7467. Min Act: -0.1700
Data Index: 7467919 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.7467. Min Act: -0.1700
Data Index: 3247431 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.7467. Min Act: -0.1700
Data Index: 1966992 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.6842. Min Act: -0.1700
Data Index: 1719726 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.7154. Min Act: -0.1700
Data Index: 109653 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.6842. Min Act: -0.1700
Data Index: 4612171 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.6842. Min Act: -0.1700
Data Index: 832480 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.6842. Min Act: -0.1700
Data Index: 2069408 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.6529. Min Act: -0.1700
Data Index: 522320 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.6217. Min Act: -0.1700
Data Index: 3611276 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.6217. Min Act: -0.1700
Data Index: 5569793 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.6217. Min Act: -0.1700
Data Index: 6294262 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.5904. Min Act: -0.1700
Data Index: 6775851 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0904. Min Range: -7.0904
Max Act: 6.6217. Min Act: -0.1700
Data Index: 1016024 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19