Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4938 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.5225. Min Act: -0.1700
Data Index: 1267825 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.4913. Min Act: -0.1700
Data Index: 1497418 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.4288. Min Act: -0.1700
Data Index: 4208170 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.4600. Min Act: -0.1700
Data Index: 4455853 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.4288. Min Act: -0.1700
Data Index: 922926 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.4288. Min Act: -0.1700
Data Index: 2518264 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.3975. Min Act: -0.1700
Data Index: 1928875 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.3350. Min Act: -0.1700
Data Index: 8679867 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.3663. Min Act: -0.1700
Data Index: 4849148 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.3038. Min Act: -0.1700
Data Index: 5050301 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.3038. Min Act: -0.1700
Data Index: 6719887 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.2100. Min Act: -0.1700
Data Index: 1574752 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.2100. Min Act: -0.1700
Data Index: 1173398 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.2100. Min Act: -0.1700
Data Index: 4483900 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.2100. Min Act: -0.1700
Data Index: 7129481 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.1788. Min Act: -0.1700
Data Index: 334777 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.1475. Min Act: -0.1700
Data Index: 1637078 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.1475. Min Act: -0.1700
Data Index: 2512038 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.1475. Min Act: -0.1700
Data Index: 2680993 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5225. Min Range: -6.5225
Max Act: 6.1475. Min Act: -0.1700
Data Index: 527691 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19