Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2511 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.7528. Min Act: -0.1700
Data Index: 420577 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.4715. Min Act: -0.1700
Data Index: 5658279 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.4090. Min Act: -0.1700
Data Index: 7674914 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.2840. Min Act: -0.1700
Data Index: 342744 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.2215. Min Act: -0.1700
Data Index: 7116166 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.1278. Min Act: -0.1700
Data Index: 7816700 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.1278. Min Act: -0.1700
Data Index: 6579935 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.0653. Min Act: -0.1700
Data Index: 8443041 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.0340. Min Act: -0.1700
Data Index: 2298714 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.0653. Min Act: -0.1700
Data Index: 7707086 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.0340. Min Act: -0.1700
Data Index: 262169 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7528. Min Range: -7.7528
Max Act: 7.0028. Min Act: -0.1700
Data Index: 3212796 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7528. Min Range: -7.7528
Max Act: 6.9715. Min Act: -0.1700
Data Index: 7049394 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7528. Min Range: -7.7528
Max Act: 6.9090. Min Act: -0.1700
Data Index: 3418816 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7528. Min Range: -7.7528
Max Act: 6.9090. Min Act: -0.1700
Data Index: 5839438 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7528. Min Range: -7.7528
Max Act: 6.8465. Min Act: -0.1700
Data Index: 1094055 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7528. Min Range: -7.7528
Max Act: 6.8153. Min Act: -0.1700
Data Index: 6673514 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7528. Min Range: -7.7528
Max Act: 6.8465. Min Act: -0.1700
Data Index: 1863951 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7528. Min Range: -7.7528
Max Act: 6.8465. Min Act: -0.1700
Data Index: 2402220 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7528. Min Range: -7.7528
Max Act: 6.8153. Min Act: -0.1700
Data Index: 3172540 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19