Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1388 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8032. Min Range: -7.8032
Max Act: 7.8032. Min Act: -0.1700
Data Index: 1932730 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8032. Min Range: -7.8032
Max Act: 7.6782. Min Act: -0.1700
Data Index: 3825708 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8032. Min Range: -7.8032
Max Act: 7.1782. Min Act: -0.1700
Data Index: 4887065 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8032. Min Range: -7.8032
Max Act: 7.0532. Min Act: -0.1700
Data Index: 5970471 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8032. Min Range: -7.8032
Max Act: 7.0220. Min Act: -0.1700
Data Index: 6106943 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.9907. Min Act: -0.1700
Data Index: 7454259 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.9595. Min Act: -0.1700
Data Index: 8095437 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.9282. Min Act: -0.1700
Data Index: 1079857 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.8345. Min Act: -0.1700
Data Index: 7639673 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.8657. Min Act: -0.1700
Data Index: 6009799 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.8345. Min Act: -0.1700
Data Index: 8337400 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.7720. Min Act: -0.1700
Data Index: 2427996 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.7720. Min Act: -0.1700
Data Index: 6572357 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.7407. Min Act: -0.1700
Data Index: 5921158 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.7407. Min Act: -0.1700
Data Index: 7156609 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.7095. Min Act: -0.1700
Data Index: 2859342 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.7095. Min Act: -0.1700
Data Index: 4250486 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.6470. Min Act: -0.1700
Data Index: 858826 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.6470. Min Act: -0.1700
Data Index: 3355252 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8032. Min Range: -7.8032
Max Act: 6.6470. Min Act: -0.1700
Data Index: 5246423 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19