Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6121 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.5587. Min Act: -0.1700
Data Index: 2747276 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.4650. Min Act: -0.1700
Data Index: 2637474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.4337. Min Act: -0.1700
Data Index: 6003960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3400. Min Act: -0.1700
Data Index: 5803373 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3400. Min Act: -0.1700
Data Index: 7794166 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3400. Min Act: -0.1700
Data Index: 8104880 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3400. Min Act: -0.1700
Data Index: 560456 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3400. Min Act: -0.1700
Data Index: 7425350 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3087. Min Act: -0.1700
Data Index: 5490681 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3087. Min Act: -0.1700
Data Index: 5006499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3087. Min Act: -0.1700
Data Index: 4833019 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3087. Min Act: -0.1700
Data Index: 6393649 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3087. Min Act: -0.1700
Data Index: 4852773 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3087. Min Act: -0.1700
Data Index: 3374313 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.3087. Min Act: -0.1700
Data Index: 3803092 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.2775. Min Act: -0.1700
Data Index: 7847992 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.2775. Min Act: -0.1700
Data Index: 2774117 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.2775. Min Act: -0.1700
Data Index: 4870154 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.2462. Min Act: -0.1700
Data Index: 4581420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5587. Min Range: -4.5587
Max Act: 4.2462. Min Act: -0.1700
Data Index: 4932106 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19