Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.9668. Min Act: -0.1700
Data Index: 4964894 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.9043. Min Act: -0.1700
Data Index: 4525042 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.9043. Min Act: -0.1700
Data Index: 5408214 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8730. Min Act: -0.1700
Data Index: 7382177 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8417. Min Act: -0.1700
Data Index: 4041256 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8417. Min Act: -0.1700
Data Index: 22654 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8417. Min Act: -0.1700
Data Index: 6784176 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8417. Min Act: -0.1700
Data Index: 2775808 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8417. Min Act: -0.1700
Data Index: 5649422 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8417. Min Act: -0.1700
Data Index: 6617583 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8417. Min Act: -0.1700
Data Index: 4093352 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8105. Min Act: -0.1700
Data Index: 5604131 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8105. Min Act: -0.1700
Data Index: 6617582 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8105. Min Act: -0.1700
Data Index: 2503785 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.8105. Min Act: -0.1700
Data Index: 2949308 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.7792. Min Act: -0.1700
Data Index: 3043406 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.7792. Min Act: -0.1700
Data Index: 1719962 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.7792. Min Act: -0.1700
Data Index: 6879680 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.7479. Min Act: -0.1700
Data Index: 6617581 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9668. Min Range: -3.9668
Max Act: 3.7479. Min Act: -0.1700
Data Index: 3516859 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19