Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4314 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.2038. Min Act: -0.1700
Data Index: 8331767 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.1100. Min Act: -0.1700
Data Index: 5155821 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0788. Min Act: -0.1700
Data Index: 5155825 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0788. Min Act: -0.1700
Data Index: 5154296 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0788. Min Act: -0.1700
Data Index: 7940043 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0788. Min Act: -0.1700
Data Index: 4107781 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0475. Min Act: -0.1700
Data Index: 3976482 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0475. Min Act: -0.1700
Data Index: 970956 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5164411 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9850. Min Act: -0.1700
Data Index: 16218 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0475. Min Act: -0.1700
Data Index: 3032210 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9850. Min Act: -0.1700
Data Index: 601146 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2038. Min Range: -5.2038
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5155822 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9850. Min Act: -0.1700
Data Index: 7441513 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9850. Min Act: -0.1700
Data Index: 4199939 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9538. Min Act: -0.1700
Data Index: 5844759 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5934787 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5600596 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9538. Min Act: -0.1700
Data Index: 5155823 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2038. Min Range: -5.2038
Max Act: 4.9538. Min Act: -0.1700
Data Index: 5999976 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19