Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 805 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.5190. Min Act: -0.1700
Data Index: 2255500 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.4252. Min Act: -0.1700
Data Index: 5134295 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.4252. Min Act: -0.1700
Data Index: 3237007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3940. Min Act: -0.1700
Data Index: 6300046 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3627. Min Act: -0.1700
Data Index: 6416338 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3627. Min Act: -0.1700
Data Index: 1941942 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3627. Min Act: -0.1700
Data Index: 6282619 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 1456760 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 390771 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 4208892 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 4930015 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 4192247 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3315. Min Act: -0.1700
Data Index: 3736677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 1135065 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 6268753 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 6069637 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 5947616 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3315. Min Act: -0.1699
Data Index: 3111373 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3315. Min Act: -0.1700
Data Index: 3111374 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5190. Min Range: -4.5190
Max Act: 4.3002. Min Act: -0.1700
Data Index: 2810547 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19