Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3339 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.4261. Min Act: -0.1700
Data Index: 5436827 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.3633. Min Act: -0.1700
Data Index: 260852 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.3320. Min Act: -0.1700
Data Index: 4360087 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.3006. Min Act: -0.1700
Data Index: 3374850 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.3006. Min Act: -0.1700
Data Index: 3788738 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2849. Min Act: -0.1700
Data Index: 6027628 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2849. Min Act: -0.1700
Data Index: 6440291 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.3006. Min Act: -0.1700
Data Index: 6855227 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2692. Min Act: -0.1700
Data Index: 4071610 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2535. Min Act: -0.1700
Data Index: 7825920 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2377. Min Act: -0.1700
Data Index: 6036466 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2377. Min Act: -0.1700
Data Index: 261571 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2063. Min Act: -0.1700
Data Index: 6378849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2220. Min Act: -0.1700
Data Index: 3064849 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2063. Min Act: -0.1700
Data Index: 8081688 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2063. Min Act: -0.1700
Data Index: 3686184 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2063. Min Act: -0.1700
Data Index: 7094271 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.2220. Min Act: -0.1700
Data Index: 2571993 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.1906. Min Act: -0.1700
Data Index: 3145753 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4261. Min Range: -3.4261
Max Act: 3.1906. Min Act: -0.1700
Data Index: 2842600 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19