Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1132 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.9066. Min Act: -0.1700
Data Index: 7300427 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.8754. Min Act: -0.1700
Data Index: 6837824 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.7816. Min Act: -0.1700
Data Index: 1790760 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.7504. Min Act: -0.1700
Data Index: 1712326 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.5629. Min Act: -0.1700
Data Index: 1208864 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.5004. Min Act: -0.1700
Data Index: 6143286 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.4691. Min Act: -0.1700
Data Index: 7023235 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.4379. Min Act: -0.1700
Data Index: 1883951 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.4066. Min Act: -0.1700
Data Index: 5683661 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.3441. Min Act: -0.1700
Data Index: 2542042 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.3754. Min Act: -0.1700
Data Index: 2586942 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.3754. Min Act: -0.1700
Data Index: 1670690 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.3754. Min Act: -0.1700
Data Index: 8404907 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.3441. Min Act: -0.1700
Data Index: 5141680 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.3441. Min Act: -0.1700
Data Index: 8469790 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.2816. Min Act: -0.1700
Data Index: 7532549 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.2816. Min Act: -0.1700
Data Index: 8636719 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.2816. Min Act: -0.1700
Data Index: 1701147 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.2816. Min Act: -0.1700
Data Index: 5530919 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9066. Min Range: -5.9066
Max Act: 5.2816. Min Act: -0.1700
Data Index: 694563 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19