Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.6754. Min Act: -0.1700
Data Index: 5478959 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.6129. Min Act: -0.1700
Data Index: 3053695 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.5816. Min Act: -0.1700
Data Index: 1113688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.5504. Min Act: -0.1700
Data Index: 6795430 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.5191. Min Act: -0.1700
Data Index: 223383 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.5191. Min Act: -0.1700
Data Index: 4224085 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.5191. Min Act: -0.1700
Data Index: 1667938 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4879. Min Act: -0.1700
Data Index: 6589664 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4566. Min Act: -0.1700
Data Index: 6895979 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4566. Min Act: -0.1700
Data Index: 3199466 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4566. Min Act: -0.1700
Data Index: 2859553 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4254. Min Act: -0.1700
Data Index: 5709103 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4254. Min Act: -0.1700
Data Index: 6042618 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4254. Min Act: -0.1700
Data Index: 1599392 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4254. Min Act: -0.1700
Data Index: 4534876 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4254. Min Act: -0.1700
Data Index: 1268938 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.4254. Min Act: -0.1700
Data Index: 161144 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.3941. Min Act: -0.1700
Data Index: 7097786 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.3941. Min Act: -0.1700
Data Index: 6349745 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6754. Min Range: -4.6754
Max Act: 4.3941. Min Act: -0.1700
Data Index: 7022618 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19