Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2130 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.8145. Min Act: -0.1700
Data Index: 2112563 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.6583. Min Act: -0.1700
Data Index: 1804933 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.6583. Min Act: -0.1700
Data Index: 7809849 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.5958. Min Act: -0.1700
Data Index: 1984013 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.5958. Min Act: -0.1700
Data Index: 465031 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.5020. Min Act: -0.1700
Data Index: 7308942 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.4708. Min Act: -0.1700
Data Index: 2191478 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.4395. Min Act: -0.1700
Data Index: 8152929 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.4083. Min Act: -0.1700
Data Index: 1899205 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.4083. Min Act: -0.1700
Data Index: 4447270 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.4395. Min Act: -0.1700
Data Index: 7152920 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.3770. Min Act: -0.1700
Data Index: 3915112 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.3458. Min Act: -0.1700
Data Index: 5308385 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.3458. Min Act: -0.1700
Data Index: 7887504 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.3458. Min Act: -0.1700
Data Index: 246633 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.3145. Min Act: -0.1700
Data Index: 898717 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.2833. Min Act: -0.1700
Data Index: 7205294 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.3145. Min Act: -0.1700
Data Index: 8056976 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.2833. Min Act: -0.1700
Data Index: 3239643 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8145. Min Range: -6.8145
Max Act: 6.2520. Min Act: -0.1700
Data Index: 5490595 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19