Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.9685. Min Act: -0.1700
Data Index: 404242 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.9060. Min Act: -0.1700
Data Index: 3949681 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.7185. Min Act: -0.1700
Data Index: 3614487 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.7185. Min Act: -0.1700
Data Index: 6095753 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.7185. Min Act: -0.1700
Data Index: 2655656 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.7185. Min Act: -0.1700
Data Index: 4885300 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.7810. Min Act: -0.1700
Data Index: 4761440 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.7185. Min Act: -0.1700
Data Index: 2240901 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.6560. Min Act: -0.1700
Data Index: 7276708 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.6560. Min Act: -0.1700
Data Index: 97708 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.7185. Min Act: -0.1700
Data Index: 3767419 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.6560. Min Act: -0.1700
Data Index: 5364238 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.6560. Min Act: -0.1700
Data Index: 5468963 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.5935. Min Act: -0.1700
Data Index: 7276706 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.6560. Min Act: -0.1700
Data Index: 8490786 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.6560. Min Act: -0.1700
Data Index: 3079191 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.6560. Min Act: -0.1700
Data Index: 4844986 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.5935. Min Act: -0.1700
Data Index: 2328541 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.6560. Min Act: -0.1700
Data Index: 6264438 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9685. Min Range: -8.9685
Max Act: 8.5310. Min Act: -0.1700
Data Index: 7396029 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19