Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4837 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0343. Min Range: -5.0343
Max Act: 5.0343. Min Act: -0.1700
Data Index: 8446505 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.9093. Min Act: -0.1700
Data Index: 6499513 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.8781. Min Act: -0.1700
Data Index: 3670267 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.8781. Min Act: -0.1700
Data Index: 8568485 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.8468. Min Act: -0.1700
Data Index: 6329374 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.8468. Min Act: -0.1700
Data Index: 233916 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.8468. Min Act: -0.1700
Data Index: 2828747 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.8156. Min Act: -0.1700
Data Index: 3721144 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.8156. Min Act: -0.1700
Data Index: 4640653 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.7843. Min Act: -0.1700
Data Index: 6470040 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.7843. Min Act: -0.1700
Data Index: 7098135 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.7218. Min Act: -0.1700
Data Index: 7513283 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.7218. Min Act: -0.1700
Data Index: 8521226 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.6906. Min Act: -0.1700
Data Index: 3721143 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.6906. Min Act: -0.1700
Data Index: 3457128 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.6593. Min Act: -0.1700
Data Index: 714977 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.6593. Min Act: -0.1700
Data Index: 3604102 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.6593. Min Act: -0.1700
Data Index: 1676723 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.6281. Min Act: -0.1700
Data Index: 2361954 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0343. Min Range: -5.0343
Max Act: 4.6281. Min Act: -0.1700
Data Index: 5783250 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19