Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.8236. Min Act: -0.1699
Data Index: 2534090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.8236. Min Act: -0.1700
Data Index: 3464848 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.8064. Min Act: -0.1699
Data Index: 6095603 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.8064. Min Act: -0.1699
Data Index: 8242429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7892. Min Act: -0.1700
Data Index: 5684328 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7892. Min Act: -0.1700
Data Index: 3241479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7720. Min Act: -0.1700
Data Index: 4817205 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7547. Min Act: -0.1700
Data Index: 1157761 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7720. Min Act: -0.1700
Data Index: 5329019 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7547. Min Act: -0.1700
Data Index: 1144017 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7633. Min Act: -0.1700
Data Index: 7988979 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7720. Min Act: -0.1697
Data Index: 2283467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7633. Min Act: -0.1700
Data Index: 6555501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7633. Min Act: -0.1700
Data Index: 2525917 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7633. Min Act: -0.1700
Data Index: 5968189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7461. Min Act: -0.1700
Data Index: 8454999 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7633. Min Act: -0.1700
Data Index: 457444 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7547. Min Act: -0.1700
Data Index: 1212637 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7461. Min Act: -0.1700
Data Index: 7935687 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8236. Min Range: -1.8236
Max Act: 1.7461. Min Act: -0.1700
Data Index: 7138569 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19