Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.6133. Min Act: -0.1661
Data Index: 7048548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.5508. Min Act: -0.1700
Data Index: 7176295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.5508. Min Act: -0.1700
Data Index: 3918763 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.5508. Min Act: -0.1697
Data Index: 7234468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.5508. Min Act: -0.1700
Data Index: 1896251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.5508. Min Act: -0.1700
Data Index: 1638898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4883. Min Act: -0.1700
Data Index: 2367111 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4883. Min Act: -0.1700
Data Index: 3323369 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4883. Min Act: -0.1700
Data Index: 4365299 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4883. Min Act: -0.1700
Data Index: 8491708 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4883. Min Act: -0.1699
Data Index: 2778251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4258. Min Act: -0.1681
Data Index: 3198452 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4258. Min Act: -0.1677
Data Index: 5743098 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4258. Min Act: -0.1700
Data Index: 5666123 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4258. Min Act: -0.1691
Data Index: 3373404 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4258. Min Act: -0.1700
Data Index: 1061665 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4258. Min Act: -0.1700
Data Index: 3452089 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4258. Min Act: -0.1700
Data Index: 6192056 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4258. Min Act: -0.1700
Data Index: 449008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6133. Min Range: -6.6133
Max Act: 6.4258. Min Act: -0.1700
Data Index: 4440451 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19