Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1494. Min Range: -9.1494
Max Act: 9.1494. Min Act: -0.1700
Data Index: 5069010 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1494. Min Range: -9.1494
Max Act: 9.0869. Min Act: -0.1700
Data Index: 549654 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1494. Min Range: -9.1494
Max Act: 9.0869. Min Act: -0.1700
Data Index: 4620190 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1494. Min Range: -9.1494
Max Act: 9.0244. Min Act: -0.1700
Data Index: 1087654 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1494. Min Range: -9.1494
Max Act: 9.0244. Min Act: -0.1700
Data Index: 2496053 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1494. Min Range: -9.1494
Max Act: 9.0244. Min Act: -0.1700
Data Index: 1087652 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.9619. Min Act: -0.1700
Data Index: 1087649 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.9619. Min Act: -0.1700
Data Index: 6712195 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8994. Min Act: -0.1700
Data Index: 4040103 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8994. Min Act: -0.1700
Data Index: 1197791 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8994. Min Act: -0.1700
Data Index: 1203256 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8994. Min Act: -0.1700
Data Index: 4446755 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8994. Min Act: -0.1700
Data Index: 1197793 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8994. Min Act: -0.1700
Data Index: 4477657 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8369. Min Act: -0.1700
Data Index: 1087648 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8369. Min Act: -0.1700
Data Index: 455381 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8369. Min Act: -0.1700
Data Index: 1156397 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8369. Min Act: -0.1700
Data Index: 1087647 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.8369. Min Act: -0.1700
Data Index: 5142487 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1494. Min Range: -9.1494
Max Act: 8.7744. Min Act: -0.1700
Data Index: 4477645 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19