Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2290 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 5422509 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 2117391 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 8466383 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 8245293 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 8087821 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 6431454 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 6138073 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 5581717 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 8693507 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 5253431 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 1283897 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 1278070 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 181654 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 5051683 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 4558919 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.4682. Min Act: -0.1700
Data Index: 3931909 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.3585. Min Act: -0.1700
Data Index: 494875 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.3585. Min Act: -0.1700
Data Index: 5240332 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.3585. Min Act: -0.1700
Data Index: 7128368 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4682. Min Range: -3.4682
Max Act: 3.3585. Min Act: -0.1700
Data Index: 7201602 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19