Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 157 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8747. Min Act: -0.1700
Data Index: 4634983 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8747. Min Act: -0.1700
Data Index: 4787837 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.9059. Min Act: -0.1700
Data Index: 498070 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8434. Min Act: -0.1700
Data Index: 5247486 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8747. Min Act: -0.1700
Data Index: 5725629 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8434. Min Act: -0.1700
Data Index: 7617566 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8434. Min Act: -0.1700
Data Index: 1198283 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8434. Min Act: -0.1700
Data Index: 3645739 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8121. Min Act: -0.1700
Data Index: 7471494 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8121. Min Act: -0.1700
Data Index: 4257625 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.7808. Min Act: -0.1700
Data Index: 3041698 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.7496. Min Act: -0.1700
Data Index: 4846931 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.8121. Min Act: -0.1700
Data Index: 5010618 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.7496. Min Act: -0.1700
Data Index: 1153289 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.7808. Min Act: -0.1700
Data Index: 7299268 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.7496. Min Act: -0.1700
Data Index: 3433964 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.7496. Min Act: -0.1700
Data Index: 7514895 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.7496. Min Act: -0.1700
Data Index: 5540683 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.6870. Min Act: -0.1700
Data Index: 7327740 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9059. Min Range: -3.9059
Max Act: 3.7183. Min Act: -0.1700
Data Index: 4326357 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19