Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.4695. Min Act: -0.1700
Data Index: 3190032 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.4070. Min Act: -0.1700
Data Index: 2361527 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2820. Min Act: -0.1700
Data Index: 4612737 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2507. Min Act: -0.1700
Data Index: 652433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2507. Min Act: -0.1699
Data Index: 4734654 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2195. Min Act: -0.1700
Data Index: 7566525 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2195. Min Act: -0.1700
Data Index: 8388043 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2195. Min Act: -0.1700
Data Index: 172948 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2195. Min Act: -0.1700
Data Index: 4075834 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2195. Min Act: -0.1700
Data Index: 524140 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1882. Min Act: -0.1700
Data Index: 191572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1570. Min Act: -0.1700
Data Index: 3237633 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1882. Min Act: -0.1700
Data Index: 1586416 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1882. Min Act: -0.1700
Data Index: 1429562 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1882. Min Act: -0.1700
Data Index: 687071 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1882. Min Act: -0.1700
Data Index: 6662340 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1882. Min Act: -0.1700
Data Index: 4187125 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1882. Min Act: -0.1700
Data Index: 2216194 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1882. Min Act: -0.1700
Data Index: 3686546 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1882. Min Act: -0.1700
Data Index: 5843236 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19