Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3788. Min Range: -8.3788
Max Act: 8.3788. Min Act: -0.1700
Data Index: 1995609 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.7538. Min Act: -0.1700
Data Index: 2904227 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.6913. Min Act: -0.1700
Data Index: 1683981 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.5663. Min Act: -0.1700
Data Index: 3332944 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.5038. Min Act: -0.1700
Data Index: 274882 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.5038. Min Act: -0.1700
Data Index: 1855133 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.5038. Min Act: -0.1700
Data Index: 4576053 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.5038. Min Act: -0.1700
Data Index: 3631070 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.4413. Min Act: -0.1700
Data Index: 320559 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.3788. Min Act: -0.1700
Data Index: 3358392 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.3788. Min Act: -0.1700
Data Index: 3236945 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.3788. Min Act: -0.1700
Data Index: 1861056 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.3476. Min Act: -0.1700
Data Index: 6594169 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.3163. Min Act: -0.1700
Data Index: 3058967 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.2851. Min Act: -0.1700
Data Index: 320557 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.2226. Min Act: -0.1700
Data Index: 6226529 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.1913. Min Act: -0.1700
Data Index: 2132941 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.2226. Min Act: -0.1700
Data Index: 7275286 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.1913. Min Act: -0.1700
Data Index: 174454 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3788. Min Range: -8.3788
Max Act: 7.1913. Min Act: -0.1700
Data Index: 3742780 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19