Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3765 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.6170. Min Act: -0.1700
Data Index: 7583036 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.4392. Min Act: -0.1700
Data Index: 712469 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.4229. Min Act: -0.1700
Data Index: 5460248 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.3902. Min Act: -0.1700
Data Index: 8011879 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.3412. Min Act: -0.1700
Data Index: 3129806 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.3412. Min Act: -0.1700
Data Index: 3694655 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.3412. Min Act: -0.1700
Data Index: 877817 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.3247. Min Act: -0.1700
Data Index: 639028 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2919. Min Act: -0.1700
Data Index: 5104503 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2919. Min Act: -0.1700
Data Index: 5988086 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2919. Min Act: -0.1695
Data Index: 769998 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2754. Min Act: -0.1700
Data Index: 4806182 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2589. Min Act: -0.1700
Data Index: 8729513 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2424. Min Act: -0.1700
Data Index: 3601296 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2093. Min Act: -0.1700
Data Index: 3325194 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2258. Min Act: -0.1700
Data Index: 1094586 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2258. Min Act: -0.1700
Data Index: 1244377 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2093. Min Act: -0.1700
Data Index: 644651 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2093. Min Act: -0.1700
Data Index: 5210363 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6170. Min Range: -2.6170
Max Act: 2.2093. Min Act: -0.1700
Data Index: 2823851 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19