Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.9325. Min Act: -0.1700
Data Index: 1715505 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.9013. Min Act: -0.1700
Data Index: 4258668 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.8388. Min Act: -0.1700
Data Index: 2074099 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.8388. Min Act: -0.1700
Data Index: 5027212 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.8075. Min Act: -0.1700
Data Index: 208401 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.7450. Min Act: -0.1700
Data Index: 1050953 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.7763. Min Act: -0.1700
Data Index: 4426578 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.7763. Min Act: -0.1700
Data Index: 4178538 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.7450. Min Act: -0.1700
Data Index: 8460381 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.6513. Min Act: -0.1700
Data Index: 6016913 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.6825. Min Act: -0.1700
Data Index: 1718508 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.6200. Min Act: -0.1700
Data Index: 1007951 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.6200. Min Act: -0.1700
Data Index: 2766048 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.5888. Min Act: -0.1700
Data Index: 277017 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.6200. Min Act: -0.1700
Data Index: 2352379 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.5575. Min Act: -0.1700
Data Index: 6202120 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.5888. Min Act: -0.1700
Data Index: 7972399 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.5575. Min Act: -0.1700
Data Index: 3515392 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.5888. Min Act: -0.1700
Data Index: 6286960 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9325. Min Range: -5.9325
Max Act: 5.5575. Min Act: -0.1700
Data Index: 4850053 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19