Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3902 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.9000. Min Act: -0.1700
Data Index: 7606416 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.4625. Min Act: -0.1700
Data Index: 846303 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.4000. Min Act: -0.1700
Data Index: 4501809 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.4000. Min Act: -0.1700
Data Index: 789526 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.4000. Min Act: -0.1700
Data Index: 2112218 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.3687. Min Act: -0.1700
Data Index: 4868238 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.2750. Min Act: -0.1700
Data Index: 6368193 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.2437. Min Act: -0.1700
Data Index: 2117448 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.2437. Min Act: -0.1700
Data Index: 7655847 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.2125. Min Act: -0.1700
Data Index: 879767 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.2125. Min Act: -0.1700
Data Index: 3293590 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.1500. Min Act: -0.1700
Data Index: 4359244 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.1500. Min Act: -0.1700
Data Index: 3371007 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.0875. Min Act: -0.1700
Data Index: 5115340 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.0875. Min Act: -0.1700
Data Index: 1798176 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.0875. Min Act: -0.1700
Data Index: 4397326 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.0875. Min Act: -0.1700
Data Index: 2177193 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.0250. Min Act: -0.1700
Data Index: 3056884 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.0250. Min Act: -0.1700
Data Index: 7099441 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9000. Min Range: -6.9000
Max Act: 6.0250. Min Act: -0.1700
Data Index: 3573944 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19