Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 141 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0956. Min Range: -8.0956
Max Act: 8.0331. Min Act: -0.1700
Data Index: 451256 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0956. Min Range: -8.0956
Max Act: 8.0956. Min Act: -0.1700
Data Index: 2393487 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.9706. Min Act: -0.1700
Data Index: 2220890 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.7831. Min Act: -0.1700
Data Index: 4088753 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.7206. Min Act: -0.1700
Data Index: 8214687 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.7206. Min Act: -0.1700
Data Index: 7534199 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.6581. Min Act: -0.1700
Data Index: 8258513 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.6581. Min Act: -0.1700
Data Index: 5534510 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5331. Min Act: -0.1700
Data Index: 1051974 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5331. Min Act: -0.1700
Data Index: 6017972 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5331. Min Act: -0.1700
Data Index: 8292035 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5331. Min Act: -0.1700
Data Index: 71417 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5331. Min Act: -0.1700
Data Index: 4175011 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5019. Min Act: -0.1700
Data Index: 5326005 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5019. Min Act: -0.1700
Data Index: 1280443 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5019. Min Act: -0.1700
Data Index: 2575021 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.4706. Min Act: -0.1700
Data Index: 2291404 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5019. Min Act: -0.1700
Data Index: 3795540 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5331. Min Act: -0.1700
Data Index: 592945 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0956. Min Range: -8.0956
Max Act: 7.5019. Min Act: -0.1700
Data Index: 4281911 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19