Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1135. Min Range: -5.1135
Max Act: 5.0823. Min Act: -0.1700
Data Index: 7679794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1135. Min Range: -5.1135
Max Act: 5.1135. Min Act: -0.1700
Data Index: 6075655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1135. Min Range: -5.1135
Max Act: 5.0510. Min Act: -0.1700
Data Index: 2432907 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1135. Min Range: -5.1135
Max Act: 5.0510. Min Act: -0.1698
Data Index: 5715007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1135. Min Range: -5.1135
Max Act: 5.0198. Min Act: -0.1700
Data Index: 6568933 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1135. Min Range: -5.1135
Max Act: 5.0198. Min Act: -0.1700
Data Index: 7882236 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.9885. Min Act: -0.1700
Data Index: 5293199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.9573. Min Act: -0.1700
Data Index: 4720386 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.9260. Min Act: -0.1699
Data Index: 2065492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.9260. Min Act: -0.1700
Data Index: 4880706 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.9260. Min Act: -0.1700
Data Index: 4046948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.9260. Min Act: -0.1700
Data Index: 1774390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.8948. Min Act: -0.1700
Data Index: 5876728 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.8948. Min Act: -0.1697
Data Index: 1450521 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.8635. Min Act: -0.1700
Data Index: 2164317 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.8948. Min Act: -0.1693
Data Index: 7135123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.8948. Min Act: -0.1700
Data Index: 2264232 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.8948. Min Act: -0.1700
Data Index: 7170921 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.8948. Min Act: -0.1700
Data Index: 5708269 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1135. Min Range: -5.1135
Max Act: 4.9260. Min Act: -0.1700
Data Index: 5330074 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19