Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0082. Min Range: -7.0082
Max Act: 7.0082. Min Act: -0.1700
Data Index: 7369888 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.9457. Min Act: -0.1700
Data Index: 3465139 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.9144. Min Act: -0.1700
Data Index: 2857449 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.8207. Min Act: -0.1700
Data Index: 1258554 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.8207. Min Act: -0.1700
Data Index: 1916050 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7582. Min Act: -0.1700
Data Index: 3697337 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7894. Min Act: -0.1700
Data Index: 1963110 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.8207. Min Act: -0.1700
Data Index: 5306536 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7582. Min Act: -0.1700
Data Index: 4938076 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7582. Min Act: -0.1700
Data Index: 6434394 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7582. Min Act: -0.1700
Data Index: 7064660 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7582. Min Act: -0.1700
Data Index: 1135036 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7269. Min Act: -0.1700
Data Index: 1097853 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7894. Min Act: -0.1700
Data Index: 5545091 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7582. Min Act: -0.1700
Data Index: 8235207 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7269. Min Act: -0.1700
Data Index: 3877657 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7269. Min Act: -0.1700
Data Index: 4104069 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7269. Min Act: -0.1700
Data Index: 5678198 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7269. Min Act: -0.1700
Data Index: 6068872 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0082. Min Range: -7.0082
Max Act: 6.7269. Min Act: -0.1700
Data Index: 7673534 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19