Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5028 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.5754. Min Act: -0.1700
Data Index: 1467616 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.5754. Min Act: -0.1700
Data Index: 1963530 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.5129. Min Act: -0.1700
Data Index: 2385598 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.4816. Min Act: -0.1700
Data Index: 7104916 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.4504. Min Act: -0.1700
Data Index: 3743612 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.4504. Min Act: -0.1700
Data Index: 6988866 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.4191. Min Act: -0.1700
Data Index: 3449248 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3566. Min Act: -0.1700
Data Index: 6543584 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3566. Min Act: -0.1700
Data Index: 6166840 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3254. Min Act: -0.1700
Data Index: 4023979 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2941. Min Act: -0.1700
Data Index: 913380 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.3254. Min Act: -0.1700
Data Index: 4464133 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2629. Min Act: -0.1700
Data Index: 3673795 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2629. Min Act: -0.1700
Data Index: 123528 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2629. Min Act: -0.1700
Data Index: 5725982 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2941. Min Act: -0.1700
Data Index: 6303964 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2316. Min Act: -0.1700
Data Index: 4007335 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2004. Min Act: -0.1700
Data Index: 2519615 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.1691. Min Act: -0.1700
Data Index: 234194 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5754. Min Range: -6.5754
Max Act: 6.2004. Min Act: -0.1700
Data Index: 8583301 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19