Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1649
Data Index: 8143187 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1698
Data Index: 3802421 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1700
Data Index: 3748530 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1696
Data Index: 8156396 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1699
Data Index: 3050627 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1700
Data Index: 2397315 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1694
Data Index: 2873690 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1700
Data Index: 4759200 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1699
Data Index: 2367461 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1700
Data Index: 7871434 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1700
Data Index: 7252115 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1691
Data Index: 6921854 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1689
Data Index: 6138410 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1698
Data Index: 3565581 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1699
Data Index: 5574523 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1699
Data Index: 5277613 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.6160. Min Act: -0.1700
Data Index: 1802874 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.5847. Min Act: -0.1698
Data Index: 934348 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.5847. Min Act: -0.1697
Data Index: 2539999 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6160. Min Range: -4.6160
Max Act: 4.5847. Min Act: -0.1700
Data Index: 1119360 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19