Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4810 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.4287. Min Act: -0.1700
Data Index: 8390215 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.3975. Min Act: -0.1700
Data Index: 1876800 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.3350. Min Act: -0.1700
Data Index: 1915338 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.3975. Min Act: -0.1700
Data Index: 2512391 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.1787. Min Act: -0.1700
Data Index: 5128956 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0225. Min Act: -0.1700
Data Index: 246882 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0225. Min Act: -0.1700
Data Index: 7860106 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0225. Min Act: -0.1700
Data Index: 4568216 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4287. Min Range: -5.4287
Max Act: 4.9912. Min Act: -0.1700
Data Index: 2273804 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0225. Min Act: -0.1700
Data Index: 4162531 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0225. Min Act: -0.1700
Data Index: 2219266 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0225. Min Act: -0.1700
Data Index: 6324252 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4287. Min Range: -5.4287
Max Act: 5.0225. Min Act: -0.1700
Data Index: 8176252 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4287. Min Range: -5.4287
Max Act: 4.9600. Min Act: -0.1700
Data Index: 1775591 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4287. Min Range: -5.4287
Max Act: 4.9600. Min Act: -0.1700
Data Index: 1568430 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4287. Min Range: -5.4287
Max Act: 4.9287. Min Act: -0.1700
Data Index: 619434 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4287. Min Range: -5.4287
Max Act: 4.9287. Min Act: -0.1700
Data Index: 6324253 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4287. Min Range: -5.4287
Max Act: 4.9287. Min Act: -0.1700
Data Index: 2212222 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4287. Min Range: -5.4287
Max Act: 4.9287. Min Act: -0.1700
Data Index: 6614342 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4287. Min Range: -5.4287
Max Act: 4.8975. Min Act: -0.1700
Data Index: 482963 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19