Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.9261. Min Act: -0.0970
Data Index: 2075157 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.5823. Min Act: -0.1700
Data Index: 3166239 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.5511. Min Act: -0.1700
Data Index: 7973400 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.5511. Min Act: -0.1700
Data Index: 5267809 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.5511. Min Act: -0.1700
Data Index: 7725792 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.5198. Min Act: -0.1700
Data Index: 59685 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.4886. Min Act: -0.1700
Data Index: 1112885 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.4886. Min Act: -0.1700
Data Index: 3303634 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.4261. Min Act: -0.1700
Data Index: 3637551 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.4261. Min Act: -0.1700
Data Index: 8256515 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.4261. Min Act: -0.1700
Data Index: 2104515 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.3948. Min Act: -0.1700
Data Index: 1024440 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.3948. Min Act: -0.1700
Data Index: 7521925 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.3948. Min Act: -0.1700
Data Index: 393109 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.3948. Min Act: -0.1700
Data Index: 2050881 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.3636. Min Act: -0.1700
Data Index: 4432863 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.3636. Min Act: -0.1700
Data Index: 8068977 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.3636. Min Act: -0.1700
Data Index: 7354194 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.3636. Min Act: -0.1700
Data Index: 3036514 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9261. Min Range: -4.9261
Max Act: 4.3636. Min Act: -0.1700
Data Index: 4034356 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19