Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.5946. Min Act: -0.1700
Data Index: 5898174 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.5634. Min Act: -0.1700
Data Index: 5898172 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.5634. Min Act: -0.1700
Data Index: 6099916 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.4384. Min Act: -0.1700
Data Index: 8523213 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.4384. Min Act: -0.1700
Data Index: 972753 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.4071. Min Act: -0.1700
Data Index: 972762 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.4071. Min Act: -0.1700
Data Index: 4019167 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.4071. Min Act: -0.1700
Data Index: 8477798 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.4071. Min Act: -0.1700
Data Index: 2702570 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 8523204 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.4071. Min Act: -0.1700
Data Index: 6877274 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.4071. Min Act: -0.1700
Data Index: 8477810 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 972759 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 5069162 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 6877251 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 8477799 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 8523194 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 8477806 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 972769 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5946. Min Range: -5.5946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 6018336 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19