Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2879 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.7144. Min Act: -0.1700
Data Index: 4373282 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.6519. Min Act: -0.1700
Data Index: 4057501 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.6206. Min Act: -0.1700
Data Index: 2332577 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.5894. Min Act: -0.1700
Data Index: 1643812 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.4644. Min Act: -0.1700
Data Index: 7794547 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.4331. Min Act: -0.1700
Data Index: 8468811 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.3706. Min Act: -0.1700
Data Index: 8605699 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.4019. Min Act: -0.1700
Data Index: 3986113 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.3706. Min Act: -0.1700
Data Index: 6167749 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.2769. Min Act: -0.1700
Data Index: 3771954 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.3081. Min Act: -0.1700
Data Index: 5007679 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.3081. Min Act: -0.1700
Data Index: 1464974 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.2769. Min Act: -0.1700
Data Index: 1084936 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.2769. Min Act: -0.1700
Data Index: 4684101 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.2769. Min Act: -0.1700
Data Index: 3868863 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.2769. Min Act: -0.1700
Data Index: 5354560 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.2144. Min Act: -0.1700
Data Index: 3577088 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.2144. Min Act: -0.1700
Data Index: 3595738 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.2144. Min Act: -0.1700
Data Index: 2984978 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7144. Min Range: -6.7144
Max Act: 6.2144. Min Act: -0.1700
Data Index: 3771953 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19